Low-level和High-level任务
Low-level任务:常见的包括 Super-Resolution,denoise, deblur, dehze, low-light enhancement, deartifacts等。简单来说,是把特定降质下的图片还原成好看的图像,现在基本上用end-to-end的模型来学习这类 ill-posed问题的求解过程,客观指标主要是PSNR,SSIM,大家指标都刷的很高。目前面临以下几点问题:
- 泛化性差,换个数据集,同种任务变现就很差。
- 客观指标与主观感受存在,GAP。
- 落地的问题,SOTA模型运算量很(上百G Flops),但实际不可能这么用。
- 偏向于解决实际问题,主要是为人服务,如手机里的各类夜景模式、美化等,都会用到相关算法。
- 市面上公司做 low-level 比较多的是手机厂商(华米OV)、安防(海康大华),相机(大疆,ISP厂商)、无人机(大疆)、视频网站(B站,快手等)。一般涉及到图像、视频增强的场景都是low-level试用的问题。
High-level任务:分类,检测,分割等。一般公开训练数据都是高品质的图像,当送入降质图像时,性能会有下降,即使网络已经经过大量的数据增强(形状,亮度,色度等变换)。真实应用场景是不可能像训练集那样完美的,采集图像的过程中会面临各种降质问题,需要两者来结合。简单来说,结合的方式分为以下几种
- 直接在降质图像上fine-tuning
- 先经过low-level的增强网络,再送入High-level的模型,两者分开训练
- 将增强网络和高层模型(如分类)联合训练
目录
HDR Imaging / Multi-Exposure Image Fusion - HDR图像生成 / 多曝光图像融合
Image Quality Assessment - 图像质量评价
Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换
Text-to-Image / Text Guided / Multi-Modal
Hyperspectral Image Reconstruction
Burst/Multi-frame Super Resolution
Spatial-Temporal Video Super-Resolution
Image Completion/Inpainting - 图像修复
Image Quality Assessment - 图像质量评价
Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换
Text-to-Image / Text Guided / Multi-Modal
Spectral Reconstruction from RGB
Perceptual Image Quality Assessment: Track 1 Full-Reference / Track 2 No-Reference
Inpainting: Track 1 Unsupervised / Track 2 Semantic
Burst Super-Resolution: Track 2 Real
HDR Imaging / Multi-Exposure Image Fusion - HDR图像生成 / 多曝光图像融合
Spatial-Temporal Video Super-Resolution
Image Completion/Inpainting - 图像修复
Image Quality Assessment - 图像质量评价
Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换
Text-to-Image / Text Guided / Multi-Modal
HDR Imaging / Multi-Exposure Image Fusion - HDR图像生成 / 多曝光图像融合
Image Quality Assessment - 图像质量评价
Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换
CVPR2023-Low-Level-Vision
Image Restoration - 图像恢复
Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
- Paper: https://arxiv.org/abs/2303.00748
- Code: GitHub - ofsoundof/GRL-Image-Restoration
- Tags: Transformer
Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective
Generative Diffusion Prior for Unified Image Restoration and Enhancement
Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank
- Paper: https://arxiv.org/abs/2303.09101
- Code: https://github.com/Huang-ShiRui/Semi-UIR
- Tags: Underwater Image Restoration
Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
- Paper: https://arxiv.org/abs/2303.15046
- Code: https://github.com/ykdai/BracketFlare
- Tags: Reflective Flare Removal
Image Reconstruction
Raw Image Reconstruction with Learned Compact Metadata
- Paper: https://arxiv.org/abs/2302.12995
- Code: GitHub - wyf0912/R2LCM: [CVPR 2023] Raw Image Reconstruction with Learned Compact Metadata
High-resolution image reconstruction with latent diffusion models from human brain activity
- Paper: High-resolution image reconstruction with latent diffusion models from human brain activity | bioRxiv
- Code: GitHub - yu-takagi/StableDiffusionReconstruction: Takagi and Nishimoto, CVPR 2023
DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration
Burst Restoration
Burstormer: Burst Image Restoration and Enhancement Transformer
Video Restoration
Blind Video Deflickering by Neural Filtering with a Flawed Atlas
- Paper: https://arxiv.org/abs/2303.08120
- Code: GitHub - ChenyangLEI/All-In-One-Deflicker: [CVPR2023] Blind Video Deflickering by Neural Filtering with a Flawed Atlas
- Tags: Deflickering
Super Resolution - 超分辨率
Image Super Resolution
Activating More Pixels in Image Super-Resolution Transformer
- Paper: https://arxiv.org/abs/2205.04437
- Code: https://github.com/XPixelGroup/HAT
- Tags: Transformer
N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution
Omni Aggregation Networks for Lightweight Image Super-Resolution
OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution
Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution
Super-Resolution Neural Operator
- Paper: https://arxiv.org/abs/2303.02584
- Code: https://github.com/2y7c3/Super-Resolution-Neural-Operator
Human Guided Ground-truth Generation for Realistic Image Super-resolution
Implicit Diffusion Models for Continuous Super-Resolution
Zero-Shot Dual-Lens Super-Resolution
- Paper:
- Code: https://github.com/XrKang/ZeDuSR
Learning Generative Structure Prior for Blind Text Image Super-resolution
- Paper: https://arxiv.org/abs/2303.14726
- Code: https://github.com/csxmli2016/MARCONet
- Tags: Text SR
Guided Depth Super-Resolution by Deep Anisotropic Diffusion
- Paper: https://arxiv.org/abs/2211.11592
- Code: GitHub - prs-eth/Diffusion-Super-Resolution: [CVPR 2023] Guided Depth Super-Resolution by Deep Anisotropic Diffusion
- Tags: Guided Depth SR
Video Super Resolution
Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting
Structured Sparsity Learning for Efficient Video Super-Resolution
Image Rescaling - 图像缩放
HyperThumbnail: Real-time 6K Image Rescaling with Rate-distortion Optimization
- Paper: https://arxiv.org/abs/2304.01064
- Code: GitHub - AbnerVictor/HyperThumbnail: [CVPR 2023] HyperThumbnail: Real-time 6K Image Rescaling with Rate-distortion Optimization. Official implementation.
Denoising - 去噪
Image Denoising
Masked Image Training for Generalizable Deep Image Denoising
Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising
- Paper: https://arxiv.org/abs/2303.14934
- Cdoe: https://github.com/nagejacob/SpatiallyAdaptiveSSID
- Tags: Self-Supervised
LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising
- Paper: https://arxiv.org/abs/2304.00534
- Code: https://github.com/Wang-XIaoDingdd/LGBPN
- Tags: Self-Supervised
Real-time Controllable Denoising for Image and Video
Deblurring - 去模糊
Image Deblurring
Structured Kernel Estimation for Photon-Limited Deconvolution
- Paper: https://arxiv.org/abs/2303.03472
- Code: https://github.com/sanghviyashiitb/structured-kernel-cvpr23
Blur Interpolation Transformer for Real-World Motion from Blur
Neumann Network with Recursive Kernels for Single Image Defocus Deblurring
- Paper:
- Code: https://github.com/csZcWu/NRKNet
Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring
Deraining - 去雨
Learning A Sparse Transformer Network for Effective Image Deraining
Dehazing - 去雾
RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors
Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
- Paper: https://arxiv.org/abs/2303.14218
- Code: GitHub - YuZheng9/C2PNet: [CVPR 2023] Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior
HDR Imaging / Multi-Exposure Image Fusion - HDR图像生成 / 多曝光图像融合
Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models
Frame Interpolation - 插帧
Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
- Paper: https://arxiv.org/abs/2303.00440
- Code: GitHub - MCG-NJU/EMA-VFI: [CVPR 2023] Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolatio
A Unified Pyramid Recurrent Network for Video Frame Interpolation
- Paper: https://arxiv.org/abs/2211.03456
- Code: GitHub - srcn-ivl/UPR-Net: Official implementation of our CVPR2023 paper "A Unified Pyramid Recurrent Network for Video Frame Interpolation"
BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation
- Paper: https://arxiv.org/abs/2304.02225
- Code: GitHub - JunHeum/BiFormer: BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation, CVPR2023
Event-based Video Frame Interpolation with Cross-Modal Asymmetric Bidirectional Motion Fields
- Paper:
- Code: GitHub - intelpro/CBMNet: Official repository of "Event-based Video Frame Interpolation with Cross-Modal Asymmetric Bidirectional Motion Fields", CVPR 2023 paper
- Tags: Event-based
Event-based Blurry Frame Interpolation under Blind Exposure
- Paper:
- Code: GitHub - WarranWeng/EBFI-BE: Event-based Blurry Frame Interpolation under Blind Exposure, CVPR2023
- Tags: Event-based
Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time
- Paper: https://arxiv.org/abs/2303.15043
- Code: GitHub - shangwei5/VIDUE: Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time (CVPR2023)
- Tags: Frame Interpolation and Deblurring
Image Enhancement - 图像增强
Low-Light Image Enhancement
Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement
Visibility Constrained Wide-band Illumination Spectrum Design for Seeing-in-the-Dark
- Paper: https://arxiv.org/abs/2303.11642
- Code: https://github.com/MyNiuuu/VCSD
- Tags: NIR2RGB
Image Matting - 图像抠图
Referring Image Matting
- Paper: https://arxiv.org/abs/2206.05149
- Code: GitHub - JizhiziLi/RIM: [CVPR 2023] Referring Image Matting
Shadow Removal - 阴影消除
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
Image Compression - 图像压缩
Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger
Context-based Trit-Plane Coding for Progressive Image Compression
Learned Image Compression with Mixed Transformer-CNN Architectures
Video Compression
Neural Video Compression with Diverse Contexts
Image Quality Assessment - 图像质量评价
Quality-aware Pre-trained Models for Blind Image Quality Assessment
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method
Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild
Style Transfer - 风格迁移
Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
Neural Preset for Color Style Transfer
CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer
StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer
- Paper: https://arxiv.org/abs/2304.02744
- Project: StyleGANSalon
Image Editing - 图像编辑
Imagic: Text-Based Real Image Editing with Diffusion Models
SINE: SINgle Image Editing with Text-to-Image Diffusion Models
CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing
DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
SIEDOB: Semantic Image Editing by Disentangling Object and Background
Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换
Text-to-Image / Text Guided / Multi-Modal
Multi-Concept Customization of Text-to-Image Diffusion
- Paper: https://arxiv.org/abs/2212.04488
- Code: GitHub - adobe-research/custom-diffusion: Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis
- Paper: https://arxiv.org/abs/2301.12959
- Code: GitHub - tobran/GALIP: [CVPR2023] A faster, smaller, and better text-to-image model for large-scale training
Scaling up GANs for Text-to-Image Synthesis
- Paper: https://arxiv.org/abs/2303.05511
- Project: GigaGAN: Scaling up GANs for Text-to-Image Synthesis
MAGVLT: Masked Generative Vision-and-Language Transformer
Freestyle Layout-to-Image Synthesis
- Paper: https://arxiv.org/abs/2303.14412
- Code: GitHub - essunny310/FreestyleNet: [CVPR 2023 Highlight] Freestyle Layout-to-Image Synthesis
Variational Distribution Learning for Unsupervised Text-to-Image Generation
Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment
- Paper: https://arxiv.org/abs/2303.17490
- Project: Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment
Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
Image-to-Image / Image Guided
LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data
- Paper: https://arxiv.org/abs/2208.14889
- Code: GitHub - KU-CVLAB/LANIT: Official repository for LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data (CVPR 2023)
Person Image Synthesis via Denoising Diffusion Model
Picture that Sketch: Photorealistic Image Generation from Abstract Sketches
Fine-Grained Face Swapping via Regional GAN Inversion
Masked and Adaptive Transformer for Exemplar Based Image Translation
- Paper: https://arxiv.org/abs/2303.17123
- Code: GitHub - AiArt-HDU/MATEBIT: Source code of "Masked and Adaptive Transformer for Exemplar Based Image Translation", accepted by CVPR 2023.
Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
- Paper: https://arxiv.org/abs/2304.03119
- Code: GitHub - Picsart-AI-Research/IPL-Zero-Shot-Generative-Model-Adaptation: [CVPR 2023] Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
Others for image generation
AdaptiveMix: Robust Feature Representation via Shrinking Feature Space
- Paper: https://arxiv.org/abs/2303.01559
- Code: GitHub - WentianZhang-ML/AdaptiveMix: This is an official pytorch implementation of 'AdaptiveMix: Robust Feature Representation via Shrinking Feature Space' (accepted by CVPR2023).
MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
- Paper: https://arxiv.org/abs/2211.09117
- Code: GitHub - LTH14/mage: A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
Regularized Vector Quantization for Tokenized Image Synthesis
Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization
Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation
Exploring Incompatible Knowledge Transfer in Few-shot Image Generation
- Paper:
- Code: GitHub - yunqing-me/RICK: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023
Post-training Quantization on Diffusion Models
- Paper: https://arxiv.org/abs/2211.15736
- Code: GitHub - 42Shawn/PTQ4DM: Implementation of Post-training Quantization on Diffusion Models (CVPR 2023)
LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation
DiffCollage: Parallel Generation of Large Content with Diffusion Models
- Paper: https://arxiv.org/abs/2303.17076
- Project: DiffCollage: Parallel Generation of Large Content with Diffusion Models
Few-shot Semantic Image Synthesis with Class Affinity Transfer
Video Generation
Conditional Image-to-Video Generation with Latent Flow Diffusion Models
- Paper: https://arxiv.org/abs/2303.13744
- Code: GitHub - nihaomiao/CVPR23_LFDM: The pytorch implementation of our CVPR 2023 paper "Conditional Image-to-Video Generation with Latent Flow Diffusion Models"
Video Probabilistic Diffusion Models in Projected Latent Space
DPE: Disentanglement of Pose and Expression for General Video Portrait Editing
- Paper: https://arxiv.org/abs/2301.06281
- Code: GitHub - Carlyx/DPE: [CVPR 2023] DPE: Disentanglement of Pose and Expression for General Video Portrait Editing
Decomposed Diffusion Models for High-Quality Video Generation
Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding
- Paper: https://arxiv.org/abs/2212.02802
- Code: GitHub - man805/Diffusion-Video-Autoencoders: An official implementation of "Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding" (CVPR 2023) in PyTorch.
MoStGAN: Video Generation with Temporal Motion Styles
- Paper:
- Code: https://github.com/xiaoqian-shen/MoStGAN
Others
DC2: Dual-Camera Defocus Control by Learning to Refocus
- Paper: https://arxiv.org/abs/2304.03285
- Project: DC2: Dual-Camera Defocus Control by Learning to Refocus
Images Speak in Images: A Generalist Painter for In-Context Visual Learning
Unifying Layout Generation with a Decoupled Diffusion Model
Unsupervised Domain Adaption with Pixel-level Discriminator for Image-aware Layout Generation
PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout
LayoutDM: Discrete Diffusion Model for Controllable Layout Generation
Make-A-Story: Visual Memory Conditioned Consistent Story Generation
Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models
LightPainter: Interactive Portrait Relighting with Freehand Scribble
- Paper: https://arxiv.org/abs/2303.12950
- Tags: Portrait Relighting
Neural Texture Synthesis with Guided Correspondence
- Paper:
- Code: https://github.com/EliotChenKJ/Guided-Correspondence-Loss
- Tags: Texture Synthesis
CF-Font: Content Fusion for Few-shot Font Generation
- Paper: https://arxiv.org/abs/2303.14017
- Code: https://github.com/wangchi95/CF-Font
- Tags: Font Generation
DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality
- Paper: https://arxiv.org/abs/2303.14585
- Code: GitHub - yizhiwang96/deepvecfont-v2: [CVPR 2023] DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality
Handwritten Text Generation from Visual Archetypes
- Paper: https://arxiv.org/abs/2303.15269
- Tags: Handwriting Generation
Disentangling Writer and Character Styles for Handwriting Generation
- Paper: https://arxiv.org/abs/2303.14736
- Code: GitHub - dailenson/SDT: This repository is the official implementation of Disentangling Writer and Character Styles for Handwriting Generation (CVPR23).
- Tags: Handwriting Generation
Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert
Uncurated Image-Text Datasets: Shedding Light on Demographic Bias
CVPR2022-Low-Level-Vision
Image Restoration - 图像恢复
Restormer: Efficient Transformer for High-Resolution Image Restoration
- Paper: https://arxiv.org/abs/2111.09881
- Code: https://github.com/swz30/Restormer
- Tags: Transformer
Uformer: A General U-Shaped Transformer for Image Restoration
- Paper: https://arxiv.org/abs/2106.03106
- Code: https://github.com/ZhendongWang6/Uformer
- Tags: Transformer
MAXIM: Multi-Axis MLP for Image Processing
- Paper: https://arxiv.org/abs/2201.02973
- Code: https://github.com/google-research/maxim
- Tags: MLP, also do image enhancement
All-In-One Image Restoration for Unknown Corruption
- Paper: http://pengxi.me/wp-content/uploads/2022/03/All-In-One-Image-Restoration-for-Unknown-Corruption.pdf
- Code: https://github.com/XLearning-SCU/2022-CVPR-AirNet
Fourier Document Restoration for Robust Document Dewarping and Recognition
- Paper: https://arxiv.org/abs/2203.09910
- Tags: Document Restoration
Exploring and Evaluating Image Restoration Potential in Dynamic Scenes
ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior
- Paper: https://arxiv.org/abs/2111.15362v2
- Code: https://github.com/ozgurkara99/ISNAS-DIP
- Tags: DIP, NAS
Deep Generalized Unfolding Networks for Image Restoration
- Paper: https://arxiv.org/abs/2204.13348
- Code: https://github.com/MC-E/Deep-Generalized-Unfolding-Networks-for-Image-Restoration
Attentive Fine-Grained Structured Sparsity for Image Restoration
Self-Supervised Deep Image Restoration via Adaptive Stochastic Gradient Langevin Dynamics
- Paper: CVPR 2022 Open Access Repository
- Tags: Self-Supervised
KNN Local Attention for Image Restoration
GIQE: Generic Image Quality Enhancement via Nth Order Iterative Degradation
TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions
- Paper: https://arxiv.org/abs/2111.14813
- Code: https://github.com/jeya-maria-jose/TransWeather
- Tags: Adverse Weather
Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model
- Paper: https://openaccess.thecvf.com/content/CVPR2022/papers/Chen_Learning_Multiple_Adverse_Weather_Removal_via_Two-Stage_Knowledge_Learning_and_CVPR_2022_paper.pdf
- Code: https://github.com/fingerk28/Two-stage-Knowledge-For-Multiple-Adverse-Weather-Removal
- Tags: Adverse Weathe(deraining, desnowing, dehazing)
Rethinking Deep Face Restoration
- Paper: CVPR 2022 Open Access Repository
- Tags: Face
RestoreFormer: High-Quality Blind Face Restoration From Undegraded Key-Value Pairs
- Paper: CVPR 2022 Open Access Repository
- Code: https://github.com/wzhouxiff/RestoreFormer
- Tags: Face
Blind Face Restoration via Integrating Face Shape and Generative Priors
- Paper: CVPR 2022 Open Access Repository
- Tags: Face
End-to-End Rubbing Restoration Using Generative Adversarial Networks
- Paper: https://arxiv.org/abs/2205.03743
- Code: https://github.com/qingfengtommy/RubbingGAN
- Tags: [Workshop], Rubbing Restoration
GenISP: Neural ISP for Low-Light Machine Cognition
- Paper: https://arxiv.org/abs/2205.03688
- Tags: [Workshop], ISP
Burst Restoration
A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift
- Paper: https://arxiv.org/abs/2203.09294
- Code: GitHub - GuoShi28/2StageAlign: The official codes of our CVPR2022 paper: A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift
- Tags: joint denoising and demosaicking
Burst Image Restoration and Enhancement
Video Restoration
Revisiting Temporal Alignment for Video Restoration
- Paper: https://arxiv.org/abs/2111.15288
- Code: GitHub - redrock303/Revisiting-Temporal-Alignment-for-Video-Restoration
Neural Compression-Based Feature Learning for Video Restoration
Bringing Old Films Back to Life
- Paper: https://arxiv.org/abs/2203.17276
- Code: https://github.com/raywzy/Bringing-Old-Films-Back-to-Life
Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global Reset Feature
- Paper: https://arxiv.org/abs/2204.00974
- Code: https://github.com/lightChaserX/neural-global-shutter
- Tags: restore clean global shutter (GS) videos
Context-Aware Video Reconstruction for Rolling Shutter Cameras
- Paper: https://arxiv.org/abs/2205.12912
- Code: https://github.com/GitCVfb/CVR
- Tags: Rolling Shutter Cameras
E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations
- Paper: https://arxiv.org/abs/2206.07578
- Tags: Event camera
- Withdrawal due to plagiarism
Hyperspectral Image Reconstruction
Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
Super Resolution - 超分辨率
Image Super Resolution
Reflash Dropout in Image Super-Resolution
- Paper: https://arxiv.org/abs/2112.12089
- Code: https://github.com/Xiangtaokong/Reflash-Dropout-in-Image-Super-Resolution
Residual Local Feature Network for Efficient Super-Resolution
- Paper: https://arxiv.org/abs/2205.07514
- Code: https://github.com/fyan111/RLFN
- Tags: won the first place in the runtime track of the NTIRE 2022 efficient super-resolution challenge
Learning the Degradation Distribution for Blind Image Super-Resolution
- Paper: https://arxiv.org/abs/2203.04962
- Code: GitHub - greatlog/UnpairedSR: This is an offical implementation of the CVPR2022's paper [Learning the Degradation Distribution for Blind Image Super-Resolution](https://arxiv.org/abs/2203.04962)
- Tags: Blind SR
Deep Constrained Least Squares for Blind Image Super-Resolution
- Paper: https://arxiv.org/abs/2202.07508
- Code: GitHub - Algolzw/DCLS: "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.
- Tags: Blind SR
Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
- Paper: https://arxiv.org/abs/2107.00986
- Code: https://github.com/zsyOAOA/BSRDM
- Tags: Blind SR
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution
- Paper: https://arxiv.org/abs/2203.09195
- Code: https://github.com/csjliang/LDL
- Tags: Real SR
Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution
- Paper: https://arxiv.org/abs/2205.03524
- Code: GitHub - lonelyhope/DADA
- Tags: Real SR
LAR-SR: A Local Autoregressive Model for Image Super-Resolution
Texture-Based Error Analysis for Image Super-Resolution
Learning to Zoom Inside Camera Imaging Pipeline
- Paper: CVPR 2022 Open Access Repository
- Tags: Raw-to-Raw domain
Task Decoupled Framework for Reference-Based Super-Resolution
- Paper: CVPR 2022 Open Access Repository
- Tags: Reference-Based
GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors
- Paper: https://arxiv.org/abs/2203.07319
- Code: GitHub - hejingwenhejingwen/GCFSR
- Tags: Face SR
A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution
- Paper: https://arxiv.org/abs/2203.09388
- Code: https://github.com/mjq11302010044/TATT
- Tags: Text SR
Learning Graph Regularisation for Guided Super-Resolution
- Paper: https://arxiv.org/abs/2203.14297
- Tags: Guided SR
Transformer-empowered Multi-scale Contextual Matching and Aggregation for Multi-contrast MRI Super-resolution
- Paper: https://arxiv.org/abs/2203.13963
- Code: https://github.com/XAIMI-Lab/McMRSR
- Tags: MRI SR
Discrete Cosine Transform Network for Guided Depth Map Super-Resolution
- Paper: https://arxiv.org/abs/2104.06977
- Code: https://github.com/Zhaozixiang1228/GDSR-DCTNet
- Tags: Guided Depth Map SR
SphereSR: 360deg Image Super-Resolution With Arbitrary Projection via Continuous Spherical Image Representation
IMDeception: Grouped Information Distilling Super-Resolution Network
- Paper: https://arxiv.org/abs/2204.11463
- Tags: [Workshop], lightweight
A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds
- Paper: https://arxiv.org/abs/2205.04910
- Code: https://github.com/WenlongZhang0517/CloserLookBlindSR
- Tags: [Workshop], Blind SR
Burst/Multi-frame Super Resolution
Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites
- Paper: https://arxiv.org/abs/2205.02031
- Code: GitHub - centreborelli/HDR-DSP-SR: Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites
- Tags: Self-Supervised, multi-exposure
Video Super Resolution
BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
- Paper: https://arxiv.org/abs/2104.13371
- Code: GitHub - ckkelvinchan/BasicVSR_PlusPlus: Official repository of "BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment"
Learning Trajectory-Aware Transformer for Video Super-Resolution
- Paper: https://arxiv.org/abs/2204.04216
- Code: GitHub - researchmm/TTVSR: [CVPR'22 Oral] TTVSR: Learning Trajectory-Aware Transformer for Video Super-Resolution
- Tags: Transformer
Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling
Investigating Tradeoffs in Real-World Video Super-Resolution
- Paper: https://arxiv.org/abs/2111.12704
- Code: https://github.com/ckkelvinchan/RealBasicVSR
- Tags: Real-world, RealBaiscVSR
Memory-Augmented Non-Local Attention for Video Super-Resolution
Stable Long-Term Recurrent Video Super-Resolution
Reference-based Video Super-Resolution Using Multi-Camera Video Triplets
- Paper: https://arxiv.org/abs/2203.14537
- Code: https://github.com/codeslake/RefVSR
- Tags: Reference-based VSR
A New Dataset and Transformer for Stereoscopic Video Super-Resolution
- Paper: https://arxiv.org/abs/2204.10039
- Code: https://github.com/H-deep/Trans-SVSR/
- Tags: Stereoscopic Video Super-Resolution
Image Rescaling - 图像缩放
Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence
Faithful Extreme Rescaling via Generative Prior Reciprocated Invertible Representations
Denoising - 去噪
Image Denoising
Self-Supervised Image Denoising via Iterative Data Refinement
- Paper: https://arxiv.org/abs/2111.14358
- Code: https://github.com/zhangyi-3/IDR
- Tags: Self-Supervised
Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots
- Paper: https://arxiv.org/abs/2203.06967
- Code: https://github.com/demonsjin/Blind2Unblind
- Tags: Self-Supervised
AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network
- Paper: https://arxiv.org/abs/2203.11799
- Code: https://github.com/wooseoklee4/AP-BSN
- Tags: Self-Supervised
CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Image
- Paper: https://arxiv.org/abs/2203.13009
- Code: GitHub - Reyhanehne/CVF-SID_PyTorch
- Tags: Self-Supervised
Noise Distribution Adaptive Self-Supervised Image Denoising Using Tweedie Distribution and Score Matching
- Paper: CVPR 2022 Open Access Repository
- Tags: Self-Supervised
Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images
- Paper: https://arxiv.org/abs/2206.01103
- Tags: Noise Modeling, Normalizing Flow
Modeling sRGB Camera Noise with Normalizing Flows
- Paper: https://arxiv.org/abs/2206.00812
- Tags: Noise Modeling, Normalizing Flow
Estimating Fine-Grained Noise Model via Contrastive Learning
- Paper: CVPR 2022 Open Access Repository
- Tags: Noise Modeling, Constrastive Learning
Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation
- Paper: https://arxiv.org/abs/2204.13873
- Tags: [Workshop]
BurstDenoising
NAN: Noise-Aware NeRFs for Burst-Denoising
- Paper: https://arxiv.org/abs/2204.04668
- Tags: NeRFs
Video Denoising
Dancing under the stars: video denoising in starlight
- Paper: https://arxiv.org/abs/2204.04210
- Code: https://github.com/monakhova/starlight_denoising/
- Tags: video denoising in starlight
Deblurring - 去模糊
Image Deblurring
Learning to Deblur using Light Field Generated and Real Defocus Images
- Paper: https://arxiv.org/abs/2204.00367
- Code: https://github.com/lingyanruan/DRBNet
- Tags: Defocus deblurring
Pixel Screening Based Intermediate Correction for Blind Deblurring
- Paper: CVPR 2022 Open Access Repository
- Tags: Blind
Deblurring via Stochastic Refinement
XYDeblur: Divide and Conquer for Single Image Deblurring
Unifying Motion Deblurring and Frame Interpolation with Events
- Paper: https://arxiv.org/abs/2203.12178
- Tags: event-based
E-CIR: Event-Enhanced Continuous Intensity Recovery
- Paper: https://arxiv.org/abs/2203.01935
- Code: https://github.com/chensong1995/E-CIR
- Tags: event-based
Video Deblurring
Multi-Scale Memory-Based Video Deblurring
Deraining - 去雨
Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond
Unpaired Deep Image Deraining Using Dual Contrastive Learning
- Paper: https://arxiv.org/abs/2109.02973
- Tags: Contrastive Learning, Unpaired
Unsupervised Deraining: Where Contrastive Learning Meets Self-similarity
- Paper: https://arxiv.org/abs/2203.11509
- Tags: Contrastive Learning, Unsupervised
Dreaming To Prune Image Deraining Networks
Dehazing - 去雾
Self-augmented Unpaired Image Dehazing via Density and Depth Decomposition
- Paper: CVPR 2022 Open Access Repository
- Code: https://github.com/YaN9-Y/D4
- Tags: Unpaired
Towards Multi-Domain Single Image Dehazing via Test-Time Training
Image Dehazing Transformer With Transmission-Aware 3D Position Embedding
Physically Disentangled Intra- and Inter-Domain Adaptation for Varicolored Haze Removal
Demoireing - 去摩尔纹
Video Demoireing with Relation-Based Temporal Consistency
Frame Interpolation - 插帧
ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
Long-term Video Frame Interpolation via Feature Propagation
Many-to-many Splatting for Efficient Video Frame Interpolation
Video Frame Interpolation with Transformer
- Paper: https://arxiv.org/abs/2205.07230
- Code: https://github.com/dvlab-research/VFIformer
- Tags: Transformer
Video Frame Interpolation Transformer
- Paper: https://arxiv.org/abs/2111.13817
- Code: https://github.com/zhshi0816/Video-Frame-Interpolation-Transformer
- Tags: Transformer
IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation
- Paper: https://arxiv.org/abs/2205.14620
- Code: GitHub - ltkong218/IFRNet: IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation (CVPR 2022)
TimeReplayer: Unlocking the Potential of Event Cameras for Video Interpolation
- Paper: https://arxiv.org/abs/2203.13859
- Tags: Event Camera
Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion
- Paper: https://arxiv.org/abs/2203.17191
- Tags: Event-based
Unifying Motion Deblurring and Frame Interpolation with Events
- Paper: https://arxiv.org/abs/2203.12178
- Tags: event-based
Multi-encoder Network for Parameter Reduction of a Kernel-based Interpolation Architecture
- Paper: https://arxiv.org/abs/2205.06723
- Tags: [Workshop]
Spatial-Temporal Video Super-Resolution
RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution
Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
- Paper: https://arxiv.org/abs/2206.04647
- Code: https://github.com/Picsart-AI-Research/VideoINR-Continuous-Space-Time-Super-Resolution
Image Enhancement - 图像增强
AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement
Exposure Correction Model to Enhance Image Quality
- Paper: https://arxiv.org/abs/2204.10648
- Code: GitHub - yamand16/ExposureCorrection
- Tags: [Workshop]
Low-Light Image Enhancement
Abandoning the Bayer-Filter to See in the Dark
- Paper: https://arxiv.org/abs/2203.04042
- Code: https://github.com/TCL-AILab/Abandon_Bayer-Filter_See_in_the_Dark
Toward Fast, Flexible, and Robust Low-Light Image Enhancement
- Paper: https://arxiv.org/abs/2204.10137
- Code: GitHub - vis-opt-group/SCI: [CVPR 2022] This is the official code for the paper "Toward Fast, Flexible, and Robust Low-Light Image Enhancement".
Deep Color Consistent Network for Low-Light Image Enhancement
SNR-Aware Low-Light Image Enhancement
- Paper: CVPR 2022 Open Access Repository
- Code: https://github.com/dvlab-research/SNR-Aware-Low-Light-Enhance
URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement
Image Harmonization - 图像协调
High-Resolution Image Harmonization via Collaborative Dual Transformationsg
- Paper: https://arxiv.org/abs/2109.06671
- Code: GitHub - bcmi/CDTNet-High-Resolution-Image-Harmonization: [CVPR 2022] We unify pixel-to-pixel transformation and color-to-color transformation in a coherent framework for high-resolution image harmonization. We also release 100 high-resolution real composite images for evaluation.
SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization
- Paper: https://arxiv.org/abs/2204.13962
- Code: GitHub - YCHang686/SCS-Co-CVPR2022: SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization (CVPR 2022)
Deep Image-based Illumination Harmonization
Image Completion/Inpainting - 图像修复
Bridging Global Context Interactions for High-Fidelity Image Completion
Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding
- Paper: https://arxiv.org/abs/2203.00867
- Code: GitHub - DQiaole/ZITS_inpainting: Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding (CVPR2022)
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
- Paper: https://arxiv.org/abs/2203.15270
- Code: GitHub - fenglinglwb/MAT: MAT: Mask-Aware Transformer for Large Hole Image Inpainting
Reduce Information Loss in Transformers for Pluralistic Image Inpainting
- Paper: https://arxiv.org/abs/2205.05076
- Code: GitHub - liuqk3/PUT: Paper 'Reduce Information Loss in Transformers for Pluralistic Image Inpainting' in CVPR2022
RePaint: Inpainting using Denoising Diffusion Probabilistic Models
- Paper: https://arxiv.org/abs/2201.09865
- Code: GitHub - andreas128/RePaint: Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022
- Tags: DDPM
Dual-Path Image Inpainting With Auxiliary GAN Inversion
SaiNet: Stereo aware inpainting behind objects with generative networks
- Paper: https://arxiv.org/abs/2205.07014
- Tags: [Workshop]
Video Inpainting
Towards An End-to-End Framework for Flow-Guided Video Inpainting
The DEVIL Is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting
DLFormer: Discrete Latent Transformer for Video Inpainting
Inertia-Guided Flow Completion and Style Fusion for Video Inpainting
Image Matting - 图像抠图
MatteFormer: Transformer-Based Image Matting via Prior-Tokens
Human Instance Matting via Mutual Guidance and Multi-Instance Refinement
- Paper: https://arxiv.org/abs/2205.10767
- Code: GitHub - nowsyn/InstMatt: Official repository for Instance Human Matting via Mutual Guidance and Multi-Instance Refinement
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation
Shadow Removal - 阴影消除
Bijective Mapping Network for Shadow Removal
Relighting
Face Relighting with Geometrically Consistent Shadows
- Paper: https://arxiv.org/abs/2203.16681
- Code: GitHub - andrewhou1/GeomConsistentFR: Official Code for Face Relighting with Geometrically Consistent Shadows (CVPR 2022)
- Tags: Face Relighting
SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Tasks
Image Stitching - 图像拼接
Deep Rectangling for Image Stitching: A Learning Baseline
Automatic Color Image Stitching Using Quaternion Rank-1 Alignment
Geometric Structure Preserving Warp for Natural Image Stitching
Image Compression - 图像压缩
Neural Data-Dependent Transform for Learned Image Compression
The Devil Is in the Details: Window-based Attention for Image Compression
ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
- Paper: https://arxiv.org/abs/2203.10897
- Code: GitHub - xiaosu-zhu/McQuic: Repository of CVPR'22 paper "Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression"
DPICT: Deep Progressive Image Compression Using Trit-Planes
Joint Global and Local Hierarchical Priors for Learned Image Compression
LC-FDNet: Learned Lossless Image Compression With Frequency Decomposition Network
Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain
- Paper: https://arxiv.org/abs/2203.16357
- Tags: Compress JPEG
SASIC: Stereo Image Compression With Latent Shifts and Stereo Attention
- Paper: CVPR 2022 Open Access Repository
- Tags: Stereo Image Compression
Deep Stereo Image Compression via Bi-Directional Coding
- Paper: CVPR 2022 Open Access Repository
- Tags: Stereo Image Compression
Learning Based Multi-Modality Image and Video Compression
PO-ELIC: Perception-Oriented Efficient Learned Image Coding
- Paper: https://arxiv.org/abs/2205.14501
- Tags: [Workshop]
Video Compression
Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction
LSVC: A Learning-Based Stereo Video Compression Framework
- Paper: CVPR 2022 Open Access Repository
- Tags: Stereo Video Compression
Enhancing VVC with Deep Learning based Multi-Frame Post-Processing
- Paper: https://arxiv.org/abs/2205.09458
- Tags: [Workshop]
Image Quality Assessment - 图像质量评价
Personalized Image Aesthetics Assessment with Rich Attributes
- Paper: https://arxiv.org/abs/2203.16754
- Tags: Aesthetics Assessment
Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment
- Paper: https://arxiv.org/abs/2204.08763
- Code: GitHub - happycaoyue/JSPL
- Tags: FR-IQA
SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment
- Paper: https://arxiv.org/abs/2205.04264
- Tags: [Workshop], compressed IQA
Image Decomposition
PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition
- Paper: CVPR 2022 Open Access Repository
- Code: GitHub - Morpheus3000/PIE-Net: Official model and network release for my CVPR2022 paper.
Deformable Sprites for Unsupervised Video Decomposition
Style Transfer - 风格迁移
CLIPstyler: Image Style Transfer with a Single Text Condition
- Paper: https://arxiv.org/abs/2112.00374
- Code: GitHub - cyclomon/CLIPstyler: Official Pytorch implementation of "CLIPstyler:Image Style Transfer with a Single Text Condition" (CVPR 2022)
- Tags: CLIP
Style-ERD: Responsive and Coherent Online Motion Style Transfer
- Paper: https://arxiv.org/abs/2203.02574
- Code: GitHub - tianxintao/Online-Motion-Style-Transfer: Code for the CVPR 2022 Paper - Style-ERD: Responsive and Coherent Online Motion Style Transfer
Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization
- Paper: https://arxiv.org/abs/2203.07740
- Code: GitHub - YBZh/EFDM: Official PyTorch codes of CVPR2022 Oral: Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization
Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer
Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation
StyTr2: Image Style Transfer With Transformers
PCA-Based Knowledge Distillation Towards Lightweight and Content-Style Balanced Photorealistic Style Transfer Models
- Paper: https://arxiv.org/abs/2203.13452
- Code: GitHub - chiutaiyin/PCA-Knowledge-Distillation: PCA-based knowledge distillation towards lightweight and content-style balanced photorealistic style transfer models
Image Editing - 图像编辑
High-Fidelity GAN Inversion for Image Attribute Editing
Style Transformer for Image Inversion and Editing
HairCLIP: Design Your Hair by Text and Reference Image
- Paper: https://arxiv.org/abs/2112.05142
- Code: GitHub - wty-ustc/HairCLIP: [CVPR 2022] HairCLIP: Design Your Hair by Text and Reference Image
- Tags: CLIP
HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing
- Paper: https://arxiv.org/abs/2111.15666
- Code: GitHub - yuval-alaluf/hyperstyle: Official Implementation for "HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing" (CVPR 2022) https://arxiv.org/abs/2111.15666
Blended Diffusion for Text-driven Editing of Natural Images
- Paper: https://arxiv.org/abs/2111.14818
- Code: GitHub - omriav/blended-diffusion: Official implementation for "Blended Diffusion for Text-driven Editing of Natural Images" [CVPR 2022]
- Tags: CLIP, Diffusion Model
FlexIT: Towards Flexible Semantic Image Translation
SemanticStyleGAN: Learning Compositonal Generative Priors for Controllable Image Synthesis and Editing
SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches
TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
- Paper: https://arxiv.org/abs/2203.17266
- Code: GitHub - BillyXYB/TransEditor: [CVPR 2022] TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
HyperInverter: Improving StyleGAN Inversion via Hypernetwork
- Paper: https://arxiv.org/abs/2112.00719
- Code: GitHub - VinAIResearch/HyperInverter: HyperInverter: Improving StyleGAN Inversion via Hypernetwork (CVPR 2022)
Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing
- Paper: https://arxiv.org/abs/2206.08357
- Code: GitHub - adobe-research/sam_inversion: [CVPR 2022] GAN inversion and editing with spatially-adaptive multiple latent layers
Brain-Supervised Image Editing
SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Color Editing
M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers
Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换
Text-to-Image / Text Guided / Multi-Modal
Text to Image Generation with Semantic-Spatial Aware GAN
- Paper: https://arxiv.org/abs/2104.00567
- Code: GitHub - wtliao/text2image: Text to Image Generation with Semantic-Spatial Aware GAN
LAFITE: Towards Language-Free Training for Text-to-Image Generation
DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis
- Paper: https://arxiv.org/abs/2008.05865
- Code: GitHub - tobran/DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis (CVPR2022 oral)
StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation
- Paper: https://arxiv.org/abs/2110.02711
- Code: GitHub - gwang-kim/DiffusionCLIP: [CVPR 2022] Official PyTorch Implementation for DiffusionCLIP: Text-guided Image Manipulation Using Diffusion Models
Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model
- Paper: https://arxiv.org/abs/2111.13333
- Code: GitHub - zipengxuc/PPE-Pytorch: Pytorch Implementation for CVPR'2022 paper ✨ "Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model"
Sound-Guided Semantic Image Manipulation
- Paper: https://arxiv.org/abs/2112.00007
- Code: https://github.com/kuai-lab/sound-guided-semantic-image-manipulation
ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation
Text-to-Image Synthesis Based on Object-Guided Joint-Decoding Transformer
Vector Quantized Diffusion Model for Text-to-Image Synthesis
AnyFace: Free-style Text-to-Face Synthesis and Manipulation
Image-to-Image / Image Guided
Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation
A Style-aware Discriminator for Controllable Image Translation
QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation
- Paper: https://arxiv.org/abs/2203.08483
- Code: GitHub - sapphire497/query-selected-attention: Official implementation for "QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation" (CVPR 2022)
InstaFormer: Instance-Aware Image-to-Image Translation with Transformer
Marginal Contrastive Correspondence for Guided Image Generation
- Paper: https://arxiv.org/abs/2204.00442
- Code: GitHub - fnzhan/UNITE: Unbalanced Feature Transport for Exemplar-based Image Translation [CVPR 2021] and Marginal Contrastive Correspondence for Guided Image Generation [CVPR 2022]
Unsupervised Image-to-Image Translation with Generative Prior
Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks
- Paper: https://arxiv.org/abs/2203.01532
- Code: GitHub - jcy132/Hneg_SRC: Official Pytorch implementation of "Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks" (CVPR 2022)
Neural Texture Extraction and Distribution for Controllable Person Image Synthesis
- Paper: https://arxiv.org/abs/2204.06160
- Code: GitHub - RenYurui/Neural-Texture-Extraction-Distribution: The PyTorch implementation for paper "Neural Texture Extraction and Distribution for Controllable Person Image Synthesis" (CVPR2022 Oral)
Unpaired Cartoon Image Synthesis via Gated Cycle Mapping
Day-to-Night Image Synthesis for Training Nighttime Neural ISPs
Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation
Self-Supervised Dense Consistency Regularization for Image-to-Image Translation
Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Model
- Paper: https://arxiv.org/abs/2103.15545
- Project Web: "Drop The GAN: In Defense of Patch Nearest Neighbors as as Single Image Generative Models
- Tags: Image manipulation
HairMapper: Removing Hair From Portraits Using GANs
Others for image generation
Attribute Group Editing for Reliable Few-shot Image Generation
Modulated Contrast for Versatile Image Synthesis
- Paper: https://arxiv.org/abs/2203.09333
- Code: GitHub - fnzhan/MoNCE: Modulated Contrast for Versatile Image Synthesis [CVPR 2022]
Interactive Image Synthesis with Panoptic Layout Generation
Autoregressive Image Generation using Residual Quantization
- Paper: https://arxiv.org/abs/2203.01941
- Code: GitHub - lucidrains/RQ-Transformer: Implementation of RQ Transformer, proposed in the paper "Autoregressive Image Generation using Residual Quantization"
Dynamic Dual-Output Diffusion Models
Exploring Dual-task Correlation for Pose Guided Person Image Generation
- Paper: https://arxiv.org/abs/2203.02910
- Code: GitHub - PangzeCheung/Dual-task-Pose-Transformer-Network: [CVPR 2022] Exploring Dual-task Correlation for Pose Guided Person Image Generation
StyleSwin: Transformer-based GAN for High-resolution Image Generation
- Paper: https://arxiv.org/abs/2112.10762
- Code: GitHub - microsoft/StyleSwin: [CVPR 2022] StyleSwin: Transformer-based GAN for High-resolution Image Generation
Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis
- Paper: https://arxiv.org/abs/2203.16898
- Code: GitHub - cszy98/SAFM: Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis (CVPR2022)
Arbitrary-Scale Image Synthesis
InsetGAN for Full-Body Image Generation
HairMapper: Removing Hair from Portraits Using GANs
- Paper: http://www.cad.zju.edu.cn/home/jin/cvpr2022/HairMapper.pdf
- Code: https://github.com/oneThousand1000/non-hair-FFHQ
OSSGAN: Open-Set Semi-Supervised Image Generation
Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis
- Paper: https://arxiv.org/abs/2204.02854
- Code: GitHub - Shi-Yupeng/RESAIL-For-SIS: Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis(CVPR2022)
A Closer Look at Few-shot Image Generation
- Paper: https://arxiv.org/abs/2205.03805
- Tags: Few-shot
Ensembling Off-the-shelf Models for GAN Training
Few-Shot Font Generation by Learning Fine-Grained Local Styles
- Paper: https://arxiv.org/abs/2205.09965
- Tags: Few-shot
Modeling Image Composition for Complex Scene Generation
Global Context With Discrete Diffusion in Vector Quantised Modelling for Image Generation
Self-supervised Correlation Mining Network for Person Image Generation
Learning To Memorize Feature Hallucination for One-Shot Image Generation
Local Attention Pyramid for Scene Image Generation
High-Resolution Image Synthesis with Latent Diffusion Models
- Paper: https://arxiv.org/abs/2112.10752
- Code: GitHub - CompVis/latent-diffusion: High-Resolution Image Synthesis with Latent Diffusion Models
Cluster-guided Image Synthesis with Unconditional Models
SphericGAN: Semi-Supervised Hyper-Spherical Generative Adversarial Networks for Fine-Grained Image Synthesis
DPGEN: Differentially Private Generative Energy-Guided Network for Natural Image Synthesis
DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
Improving GAN Equilibrium by Raising Spatial Awareness
**Polymorphic-GAN: Generating Aligned Samples Across Multiple Domains With Learned Morph Maps **
Manifold Learning Benefits GANs
Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data
- Paper: https://arxiv.org/abs/2204.04950
- Code: GitHub - FriedRonaldo/Primitives-PS: Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data - Official PyTorch Implementation (CVPR 2022)
On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models
- Paper: https://arxiv.org/abs/2205.03859
- Tags: [Workshop]
Generate and Edit Your Own Character in a Canonical View
- Paper: https://arxiv.org/abs/2205.02974
- Tags: [Workshop]
StyLandGAN: A StyleGAN based Landscape Image Synthesis using Depth-map
- Paper: https://arxiv.org/abs/2205.06611
- Tags: [Workshop]
Overparameterization Improves StyleGAN Inversion
- Paper: https://arxiv.org/abs/2205.06304
- Tags: [Workshop]
Video Generation/Synthesis
Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning
Playable Environments: Video Manipulation in Space and Time
StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2
- Paper: https://kaust-cair.s3.amazonaws.com/stylegan-v/stylegan-v-paper.pdf
- Code: https://github.com/universome/stylegan-v
Thin-Plate Spline Motion Model for Image Animation
- Paper: https://arxiv.org/abs/2203.14367
- Code: GitHub - yoyo-nb/Thin-Plate-Spline-Motion-Model: [CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.
Make It Move: Controllable Image-to-Video Generation with Text Descriptions
- Paper: https://arxiv.org/abs/2112.02815
- Code: GitHub - Youncy-Hu/MAGE: Make It Move: Controllable Image-to-Video Generation with Text Descriptions
Diverse Video Generation from a Single Video
- Paper: https://arxiv.org/abs/2205.05725
- Tags: [Workshop]
Others
GAN-Supervised Dense Visual Alignment
ClothFormer:Taming Video Virtual Try-on in All Module
- Paper: https://arxiv.org/abs/2204.12151
- Tags: Video Virtual Try-on
Iterative Deep Homography Estimation
- Paper: https://arxiv.org/abs/2203.15982
- Code: GitHub - imdumpl78/IHN: This is the open source implementation of the CVPR2022 paper "Iterative Deep Homography Estimation"
Style-Structure Disentangled Features and Normalizing Flows for Diverse Icon Colorization
- Paper: https://openaccess.thecvf.com/content/CVPR2022/papers/Li_Style-Structure_Disentangled_Features_and_Normalizing_Flows_for_Diverse_Icon_Colorization_CVPR_2022_paper.pdf
- Code: GitHub - djosix/IconFlow: Code for "Style-Structure Disentangled Features and Normalizing Flows for Diverse Icon Colorization", CVPR 2022.
Unsupervised Homography Estimation with Coplanarity-Aware GAN
- Paper: https://arxiv.org/abs/2205.03821
- Code: GitHub - megvii-research/HomoGAN: This is the official implementation of HomoGAN, CVPR2022
Diverse Image Outpainting via GAN Inversion
- Paper: https://arxiv.org/abs/2104.00675
- Code: GitHub - yccyenchicheng/InOut: Diverse Image Outpainting via GAN Inversion
On Aliased Resizing and Surprising Subtleties in GAN Evaluation
- Paper: https://arxiv.org/abs/2104.11222
- Code: GitHub - GaParmar/clean-fid: PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
Patch-wise Contrastive Style Learning for Instagram Filter Removal
- Paper: https://arxiv.org/abs/2204.07486
- Code: GitHub - birdortyedi/cifr-pytorch
- Tags: [Workshop]
NTIRE2022
New Trends in Image Restoration and Enhancement workshop and challenges on image and video processing.
Spectral Reconstruction from RGB
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
- Paper: https://arxiv.org/abs/2204.07908
- Code: GitHub - caiyuanhao1998/MST-plus-plus: "MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction" (CVPRW 2022) & (Winner of NTIRE 2022 Spectral Recovery Challenge) and a toolbox for spectral reconstruction
- Tags: 1st place
Perceptual Image Quality Assessment: Track 1 Full-Reference / Track 2 No-Reference
MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
- Paper: https://arxiv.org/abs/2204.08958
- Code: GitHub - IIGROUP/MANIQA: [CVPRW 2022] MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
- Tags: 1st place for track2
Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network
- Paper: https://arxiv.org/abs/2204.10485
- Code: GitHub - IIGROUP/AHIQ: [CVPRW 2022] Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network
- Tags: 1st place for track1
MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion
- Paper: https://arxiv.org/abs/2205.10101
- Tags: 2nd place in track2
Conformer and Blind Noisy Students for Improved Image Quality Assessment
Inpainting: Track 1 Unsupervised / Track 2 Semantic
GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting
- Paper: https://arxiv.org/abs/2205.07162
- Tags: ranked first in terms of PSNR, LPIPS and SSIM in the track1
Efficient Super-Resolution
- Report: https://arxiv.org/abs/2205.05675
ShuffleMixer: An Efficient ConvNet for Image Super-Resolution
- Paper: https://arxiv.org/abs/2205.15175
- Code: https://github.com/sunny2109/MobileSR-NTIRE2022
- Tags: Winner of the model complexity track
Edge-enhanced Feature Distillation Network for Efficient Super-Resolution
Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution
- Paper: https://arxiv.org/abs/2204.08759
- Code: GitHub - NJU-Jet/FMEN: Lowest memory consumption and second shortest runtime in NTIRE 2022 challenge on Efficient Super-Resolution
- Tags: Lowest memory consumption and second shortest runtime
Blueprint Separable Residual Network for Efficient Image Super-Resolution
- Paper: https://arxiv.org/abs/2205.05996
- Code: GitHub - xiaom233/BSRN: Blueprint Separable Residual Network for Efficient Image Super-Resolution
- Tags: 1st place in model complexity track
Night Photography Rendering
Rendering Nighttime Image Via Cascaded Color and Brightness Compensation
- Paper: https://arxiv.org/abs/2204.08970
- Code: GitHub - NJUVISION/CBUnet: Official code of the "Rendering Nighttime Image Via Cascaded Color and Brightness Compensation"
- Tags: 2nd place
Super-Resolution and Quality Enhancement of Compressed Video: Track1 (Quality enhancement) / Track2 (Quality enhancement and x2 SR) / Track3 (Quality enhancement and x4 SR)
- Report: https://arxiv.org/abs/2204.09314
- Homepage: GitHub - RenYang-home/NTIRE22_VEnh_SR
Progressive Training of A Two-Stage Framework for Video Restoration
- Paper: https://arxiv.org/abs/2204.09924
- Code: GitHub - ryanxingql/winner-ntire22-vqe: Our method and experience of wining the NTIRE22 challenge on video quality enhancement
- Tags: 1st place in track1 and track2, 2nd place in track3
High Dynamic Range (HDR): Track 1 Low-complexity (fidelity constrain) / Track 2 Fidelity (low-complexity constrain)
- Report: https://arxiv.org/abs/2205.12633
Efficient Progressive High Dynamic Range Image Restoration via Attention and Alignment Network
- Paper: https://arxiv.org/abs/2204.09213
- Tags: 2nd palce of both two tracks
Stereo Super-Resolution
- Report: https://arxiv.org/abs/2204.09197
Parallel Interactive Transformer
- Code: GitHub - chaineypung/CVPR-NTIRE2022-Parallel-Interactive-Transformer: This is the source code of the 7th place solution for stereo image super resolution task in 2022 CVPR NTIRE challenge.
- Tags: 7st place
Burst Super-Resolution: Track 2 Real
BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment
- Code: https://github.com/Algolzw/BSRT
- Tags: 1st place
ECCV2022-Low-Level-Vision
Image Restoration - 图像恢复
Simple Baselines for Image Restoration
D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration
Seeing Far in the Dark with Patterned Flash
- Paper: https://arxiv.org/abs/2207.12570
- Code: https://github.com/zhsun0357/Seeing-Far-in-the-Dark-with-Patterned-Flash
BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
Improving Image Restoration by Revisiting Global Information Aggregation
Fast Two-step Blind Optical Aberration Correction
- Paper: https://arxiv.org/abs/2208.00950
- Code: https://github.com/teboli/fast_two_stage_psf_correction
- Tags: Optical Aberration Correction
VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
- Paper: https://arxiv.org/abs/2205.06803
- Code: https://github.com/TencentARC/VQFR
- Tags: Blind Face Restoration
RAWtoBit: A Fully End-to-end Camera ISP Network
- Paper: https://arxiv.org/abs/2208.07639
- Tags: ISP and Image Compression
Transform your Smartphone into a DSLR Camera: Learning the ISP in the Wild
- Paper: https://arxiv.org/abs/2203.10636
- Code: https://github.com/4rdhendu/TransformPhone2DSLR
- Tags: ISP
Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model
- Paper: https://arxiv.org/abs/2207.10040
- Code: https://github.com/VITA-Group/TurbNet
- Tags: Atmospheric Turbulence Mitigation, Transformer
Modeling Mask Uncertainty in Hyperspectral Image Reconstruction
- Paper: https://arxiv.org/abs/2112.15362
- Code: https://github.com/Jiamian-Wang/mask_uncertainty_spectral_SCI
- Tags: Hyperspectral Image Reconstruction
TAPE: Task-Agnostic Prior Embedding for Image Restoration
DRCNet: Dynamic Image Restoration Contrastive Network
ART-SS: An Adaptive Rejection Technique for Semi-Supervised Restoration for Adverse Weather-Affected Images
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/rajeevyasarla/ART-SS
- Tags: Adverse Weather
Spectrum-Aware and Transferable Architecture Search for Hyperspectral Image Restoration
- Paper: ECVA | European Computer Vision Association
- Tags: Hyperspectral Image Restoration
Seeing through a Black Box: Toward High-Quality Terahertz Imaging via Subspace-and-Attention Guided Restoration
- Paper: ECVA | European Computer Vision Association
- Tags: Terahertz Imaging
JPEG Artifacts Removal via Contrastive Representation Learning
- Paper: ECVA | European Computer Vision Association
- Tags: JPEG Artifacts Removal
Zero-Shot Learning for Reflection Removal of Single 360-Degree Image
- Paper: ECVA | European Computer Vision Association
- Tags: Reflection Removal
Overexposure Mask Fusion: Generalizable Reverse ISP Multi-Step Refinement
- Paper: https://arxiv.org/abs/2210.11511
- Code: https://github.com/SenseBrainTech/overexposure-mask-reverse-ISP
- Tagss: [Workshop], Reversed ISP
Video Restoration
Video Restoration Framework and Its Meta-Adaptations to Data-Poor Conditions
Super Resolution - 超分辨率
Image Super Resolution
ARM: Any-Time Super-Resolution Method
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
CADyQ : Contents-Aware Dynamic Quantization for Image Super Resolution
Image Super-Resolution with Deep Dictionary
Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution
Adaptive Patch Exiting for Scalable Single Image Super-Resolution
Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution
- Paper: https://arxiv.org/abs/2207.12987
- Code: https://github.com/zhjy2016/SPLUT
- Tags: Efficient
MuLUT: Cooperating Mulitple Look-Up Tables for Efficient Image Super-Resolution
- Paper: https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136780234.pdf
- Code: https://github.com/ddlee-cn/MuLUT
- Tags: Efficient
Efficient Long-Range Attention Network for Image Super-resolution
Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/huxiaotaostasy/MGA-scheme
Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution
- Paper: https://arxiv.org/abs/2207.09156
- Code: https://github.com/palmdong/MMSR
- Tags: Self-Supervised
Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations
- Paper: https://arxiv.org/abs/2203.01325
- Code: https://github.com/cszhilu1998/SelfDZSR
- Tags: Self-Supervised, Reference-based
Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution
- Paper: http://www4.comp.polyu.edu.hk/~cslzhang/paper/ECCV2022_DASR.pdf
- Code: https://github.com/csjliang/DASR
- Tags: Real-World
D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution
- Paper: https://arxiv.org/abs/2103.14373
- Code: https://github.com/megvii-research/D2C-SR
- Tag: Real-World
MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution
- Paper: https://arxiv.org/abs/2205.05065
- Code: https://github.com/TencentARC/MM-RealSR
- Tag: Real-World
KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution
- Paper: https://arxiv.org/abs/2209.10305
- Code: https://github.com/jiahong-fu/KXNet
- Tags: Blind
From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution
- Paper: https://arxiv.org/abs/2210.00752
- Code: https://github.com/csxmli2016/ReDegNet
- Tags: Blind
Unfolded Deep Kernel Estimation for Blind Image Super-Resolution
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/natezhenghy/UDKE
- Tags: Blind
Uncertainty Learning in Kernel Estimation for Multi-stage Blind Image Super-Resolution
- Paper: ECVA | European Computer Vision Association
- Tags: Blind
Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images
- Paper: https://arxiv.org/abs/2210.04198
- Code: https://github.com/HaomingCai/SRPO
- Tags: Rasterized Images
Reference-based Image Super-Resolution with Deformable Attention Transformer
- Paper: https://arxiv.org/abs/2207.11938
- Code: https://github.com/caojiezhang/DATSR
- Tags: Reference-based, Transformer
RRSR:Reciprocal Reference-Based Image Super-Resolution with Progressive Feature Alignment and Selection
- Paper: ECVA | European Computer Vision Association
- Tags: Reference-based
Boosting Event Stream Super-Resolution with a Recurrent Neural Network
- Paper: ECVA | European Computer Vision Association
- Tags: Event
HST: Hierarchical Swin Transformer for Compressed Image Super-resolution
- Paper: https://arxiv.org/abs/2208.09885
- Tags: [Workshop-AIM2022]
Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration
- Paper: https://arxiv.org/abs/2209.11345
- Code: https://github.com/mv-lab/swin2sr
- Tags: [Workshop-AIM2022]
Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution
- Paper: https://arxiv.org/abs/2208.11609
- Code: https://github.com/Algolzw/NCNet
- Tags: [Workshop-AIM2022]
Video Super Resolution
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution
- Paper: https://arxiv.org/abs/2208.03012
- Code: https://github.com/researchmm/FTVSR
- Tags: Compressed Video SR
A Codec Information Assisted Framework for Efficient Compressed Video Super-Resolution
- Paper: ECVA | European Computer Vision Association
- Tags: Compressed Video SR
Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Dataset
Denoising - 去噪
Image Denoising
Deep Semantic Statistics Matching (D2SM) Denoising Network
Fast and High Quality Image Denoising via Malleable Convolution
Video Denoising
Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-ahead Forward Ones
TempFormer: Temporally Consistent Transformer for Video Denoising
- Paper: ECVA | European Computer Vision Association
- Tags: Transformer
Deblurring - 去模糊
Image Deblurring
Learning Degradation Representations for Image Deblurring
Stripformer: Strip Transformer for Fast Image Deblurring
- Paper: ECVA | European Computer Vision Association
- Tags: Transformer
Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
- Paper: https://arxiv.org/abs/2207.10123
- Code: https://github.com/zzh-tech/Animation-from-Blur
- Tags: recovering detailed motion from a single motion-blurred image
United Defocus Blur Detection and Deblurring via Adversarial Promoting Learning
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/wdzhao123/APL
- Tags: Defocus Blur
Realistic Blur Synthesis for Learning Image Deblurring
- Paper: ECVA | European Computer Vision Association
- Tags: Blur Synthesis
Event-based Fusion for Motion Deblurring with Cross-modal Attention
- Paper:https://arxiv.org/abs/2112.00167
- Code: https://github.com/AHupuJR/EFNet
- Tags: Event-based
Event-Guided Deblurring of Unknown Exposure Time Videos
- Paper: ECVA | European Computer Vision Association
- Tags: Event-based
Video Deblurring
Spatio-Temporal Deformable Attention Network for Video Deblurring
Efficient Video Deblurring Guided by Motion Magnitude
ERDN: Equivalent Receptive Field Deformable Network for Video Deblurring
DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
- Paper: https://arxiv.org/abs/2111.09985
- Code: https://github.com/JihyongOh/DeMFI
- Tags: Joint Deblurring and Frame Interpolation
Towards Real-World Video Deblurring by Exploring Blur Formation Process
- Paper: https://arxiv.org/abs/2208.13184
- Tags: [Workshop-AIM2022]
Image Decomposition
Blind Image Decomposition
Deraining - 去雨
Not Just Streaks: Towards Ground Truth for Single Image Deraining
Rethinking Video Rain Streak Removal: A New Synthesis Model and a Deraining Network with Video Rain Prior
Dehazing - 去雾
Frequency and Spatial Dual Guidance for Image Dehazing
Perceiving and Modeling Density for Image Dehazing
- Paper: https://arxiv.org/abs/2111.09733
- Code: https://github.com/Owen718/ECCV22-Perceiving-and-Modeling-Density-for-Image-Dehazing
Boosting Supervised Dehazing Methods via Bi-Level Patch Reweighting
Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning
Demoireing - 去摩尔纹
Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
HDR Imaging / Multi-Exposure Image Fusion - HDR图像生成 / 多曝光图像融合
Exposure-Aware Dynamic Weighted Learning for Single-Shot HDR Imaging
Ghost-free High Dynamic Range Imaging with Context-aware Transformer
Selective TransHDR: Transformer-Based Selective HDR Imaging Using Ghost Region Mask
HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields
Towards Real-World HDRTV Reconstruction: A Data Synthesis-Based Approach
Image Fusion
FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion
Recurrent Correction Network for Fast and Efficient Multi-modality Image Fusion
Neural Image Representations for Multi-Image Fusion and Layer Separation
- Paper: https://arxiv.org/abs/2108.01199
- Code: Seonghyeon Nam | Neural Image Representations for Multi-Image Fusion and Layer Separation
Fusion from Decomposition: A Self-Supervised Decomposition Approach for Image Fusion
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/erfect2020/DecompositionForFusion
Frame Interpolation - 插帧
Real-Time Intermediate Flow Estimation for Video Frame Interpolation
FILM: Frame Interpolation for Large Motion
Video Interpolation by Event-driven Anisotropic Adjustment of Optical Flow
Learning Cross-Video Neural Representations for High-Quality Frame Interpolation
Deep Bayesian Video Frame Interpolation
A Perceptual Quality Metric for Video Frame Interpolation
DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
- Paper: https://arxiv.org/abs/2111.09985
- Code: https://github.com/JihyongOh/DeMFI
- Tags: Joint Deblurring and Frame Interpolation
Spatial-Temporal Video Super-Resolution
Towards Interpretable Video Super-Resolution via Alternating Optimization
Image Enhancement - 图像增强
Local Color Distributions Prior for Image Enhancement
- Paper: https://www.cs.cityu.edu.hk/~rynson/papers/eccv22b.pdf
- Code: https://github.com/hywang99/LCDPNet
SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement
Neural Color Operators for Sequential Image Retouching
Deep Fourier-Based Exposure Correction Network with Spatial-Frequency Interaction
- Paper: ECVA | European Computer Vision Association
- Tags: Exposure Correction
Uncertainty Inspired Underwater Image Enhancement
- Paper: ECVA | European Computer Vision Association
- Tags: Underwater Image Enhancement
NEST: Neural Event Stack for Event-Based Image Enhancement
- Paper: ECVA | European Computer Vision Association
- Tags: Event-Based
Low-Light Image Enhancement
LEDNet: Joint Low-light Enhancement and Deblurring in the Dark
Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression
Image Harmonization - 图像协调
Harmonizer: Learning to Perform White-Box Image and Video Harmonization
DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization
Semantic-Guided Multi-Mask Image Harmonization
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/XuqianRen/Semantic-guided-Multi-mask-Image-Harmonization
Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
Image Completion/Inpainting - 图像修复
Learning Prior Feature and Attention Enhanced Image Inpainting
Perceptual Artifacts Localization for Inpainting
High-Fidelity Image Inpainting with GAN Inversion
Unbiased Multi-Modality Guidance for Image Inpainting
Image Inpainting with Cascaded Modulation GAN and Object-Aware Training
Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation
Diverse Image Inpainting with Normalizing Flow
Hourglass Attention Network for Image Inpainting
Perceptual Artifacts Localization for Inpainting
Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context
- Paper: https://arxiv.org/abs/2207.10273
- Code: https://github.com/lcy0604/CTRNet
- Tags: Text Removal
The Surprisingly Straightforward Scene Text Removal Method with Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/naver/garnet
- Tags: Text Removal
Video Inpainting
Error Compensation Framework for Flow-Guided Video Inpainting
Flow-Guided Transformer for Video Inpainting
Image Colorization - 图像上色
Eliminating Gradient Conflict in Reference-based Line-art Colorization
Bridging the Domain Gap towards Generalization in Automatic Colorization
CT2: Colorization Transformer via Color Tokens
PalGAN: Image Colorization with Palette Generative Adversarial Networks
BigColor: Colorization using a Generative Color Prior for Natural Images
- Paper: https://kimgeonung.github.io/assets/bigcolor/bigcolor_main.pdf
- Code: https://github.com/KIMGEONUNG/BigColor
Semantic-Sparse Colorization Network for Deep Exemplar-Based Colorization
ColorFormer: Image Colorization via Color Memory Assisted Hybrid-Attention Transformer
L-CoDer: Language-Based Colorization with Color-Object Decoupling Transformer
Colorization for In Situ Marine Plankton Images
Image Matting - 图像抠图
TransMatting: Enhancing Transparent Objects Matting with Transformers
One-Trimap Video Matting
Shadow Removal - 阴影消除
Style-Guided Shadow Removal
Image Compression - 图像压缩
Optimizing Image Compression via Joint Learning with Denoising
Implicit Neural Representations for Image Compression
- Paper: https://arxiv.org/abs/2112.04267
- Code:https://github.com/YannickStruempler/inr_based_compression
Expanded Adaptive Scaling Normalization for End to End Image Compression
Content-Oriented Learned Image Compression
Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression
Content Adaptive Latents and Decoder for Neural Image Compression
Video Compression
AlphaVC: High-Performance and Efficient Learned Video Compression
CANF-VC: Conditional Augmented Normalizing Flows for Video Compression
Neural Video Compression Using GANs for Detail Synthesis and Propagation
Image Quality Assessment - 图像质量评价
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
Shift-tolerant Perceptual Similarity Metric
Telepresence Video Quality Assessment
A Perceptual Quality Metric for Video Frame Interpolation
Relighting/Delighting
Deep Portrait Delighting
Geometry-Aware Single-Image Full-Body Human Relighting
NeRF for Outdoor Scene Relighting
Physically-Based Editing of Indoor Scene Lighting from a Single Image
Style Transfer - 风格迁移
CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer
Image-Based CLIP-Guided Essence Transfer
Learning Graph Neural Networks for Image Style Transfer
WISE: Whitebox Image Stylization by Example-based Learning
Language-Driven Artistic Style Transfer
MoDA: Map Style Transfer for Self-Supervised Domain Adaptation of Embodied Agents
JoJoGAN: One Shot Face Stylization
EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer
- Paper: https://arxiv.org/abs/2207.09840
- Code: https://github.com/Chenyu-Yang-2000/EleGANt
- Tags: Makeup Transfer
RamGAN: Region Attentive Morphing GAN for Region-Level Makeup Transfer
- Paper: ECVA | European Computer Vision Association
- Tags: Makeup Transfer
Image Editing - 图像编辑
Context-Consistent Semantic Image Editing with Style-Preserved Modulation
GAN with Multivariate Disentangling for Controllable Hair Editing
- Paper: https://raw.githubusercontent.com/XuyangGuo/xuyangguo.github.io/main/database/CtrlHair/CtrlHair.pdf
- Code: https://github.com/XuyangGuo/CtrlHair
Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing
High-fidelity GAN Inversion with Padding Space
Text2LIVE: Text-Driven Layered Image and Video Editing
IntereStyle: Encoding an Interest Region for Robust StyleGAN Inversion
Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment
HairNet: Hairstyle Transfer with Pose Changes
End-to-End Visual Editing with a Generatively Pre-trained Artist
The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing
Scraping Textures from Natural Images for Synthesis and Editing
VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance
Editing Out-of-Domain GAN Inversion via Differential Activations
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/HaoruiSong622/Editing-Out-of-Domain
ChunkyGAN: Real Image Inversion via Segments
FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations
A Style-Based GAN Encoder for High Fidelity Reconstruction of Images and Videos
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/InterDigitalInc/FeatureStyleEncoder
Rayleigh EigenDirections (REDs): Nonlinear GAN latent space traversals for multidimensional features
Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换
Text-to-Image / Text Guided / Multi-Modal
TIPS: Text-Induced Pose Synthesis
TISE: A Toolbox for Text-to-Image Synthesis Evaluation
Learning Visual Styles from Audio-Visual Associations
Multimodal Conditional Image Synthesis with Product-of-Experts GANs
NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion
Make-a-Scene: Scene-Based Text-to-Image Generation with Human Priors
Trace Controlled Text to Image Generation
Audio-Driven Stylized Gesture Generation with Flow-Based Model
No Token Left Behind: Explainability-Aided Image Classification and Generation
Image-to-Image / Image Guided
End-to-end Graph-constrained Vectorized Floorplan Generation with Panoptic Refinement
ManiFest: Manifold Deformation for Few-shot Image Translation
VecGAN: Image-to-Image Translation with Interpretable Latent Directions
DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation
Cross Attention Based Style Distribution for Controllable Person Image Synthesis
Vector Quantized Image-to-Image Translation
URUST: Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization
General Object Pose Transformation Network from Unpaired Data
Unpaired Image Translation via Vector Symbolic Architectures
Supervised Attribute Information Removal and Reconstruction for Image Manipulation
Bi-Level Feature Alignment for Versatile Image Translation and Manipulation
Multi-Curve Translator for High-Resolution Photorealistic Image Translation
CoGS: Controllable Generation and Search from Sketch and Style
AgeTransGAN for Facial Age Transformation with Rectified Performance Metrics
Others for image generation
StyleLight: HDR Panorama Generation for Lighting Estimation and Editing
Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling
GAN Cocktail: mixing GANs without dataset access
Compositional Visual Generation with Composable Diffusion Models
- Paper: https://arxiv.org/abs/2206.01714
- Code: https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
Adaptive-Feature-Interpolation-for-Low-Shot-Image-Generation
- Paper: https://arxiv.org/abs/2112.02450
- Code: https://github.com/dzld00/Adaptive-Feature-Interpolation-for-Low-Shot-Image-Generation
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pretrained StyleGAN
WaveGAN: An Frequency-aware GAN for High-Fidelity Few-shot Image Generation
FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs
Auto-regressive Image Synthesis with Integrated Quantization
PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
- Paper: https://arxiv.org/abs/2207.10271
- Code: https://github.com/bcmi/DeltaGAN-Few-Shot-Image-Generation
Generator Knows What Discriminator Should Learn in Unconditional GANs
Hierarchical Semantic Regularization of Latent Spaces in StyleGANs
- Paper: https://arxiv.org/abs/2208.03764
- Code: https://drive.google.com/file/d/1gzHTYTgGBUlDWyN_Z3ORofisQrHChg_n/view
FurryGAN: High Quality Foreground-aware Image Synthesis
- Paper: https://arxiv.org/abs/2208.10422
- Project: FurryGAN
Improving GANs for Long-Tailed Data through Group Spectral Regularization
- Paper: https://arxiv.org/abs/2208.09932
- Code: https://drive.google.com/file/d/1aG48i04Q8mOmD968PAgwEvPsw1zcS4Gk/view
Exploring Gradient-based Multi-directional Controls in GANs
Improved Masked Image Generation with Token-Critic
Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation
- Paper: https://arxiv.org/abs/2209.05968
- Project: Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation
Any-Resolution Training for High-Resolution Image Synthesis
BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-Aided Adversarial Learning
Few-Shot Image Generation with Mixup-Based Distance Learning
StyleGAN-Human: A Data-Centric Odyssey of Human Generation
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/stylegan-human/StyleGAN-Human
StyleFace: Towards Identity-Disentangled Face Generation on Megapixels
Contrastive Learning for Diverse Disentangled Foreground Generation
BLT: Bidirectional Layout Transformer for Controllable Layout Generation
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/google-research/google-research/tree/master/layout-blt
Entropy-Driven Sampling and Training Scheme for Conditional Diffusion Generation
Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
DuelGAN: A Duel between Two Discriminators Stabilizes the GAN Training
Video Generation
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
Controllable Video Generation through Global and Local Motion Dynamics
- Paper: https://arxiv.org/abs/2204.06558
- Code: GitHub - Araachie/glass: Controllable Video Generation through Global and Local Motion Dynamics. In ECCV, 2022
Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis
Synthesizing Light Field Video from Monocular Video
- Paper: https://arxiv.org/abs/2207.10357
- Code: https://github.com/ShrisudhanG/Synthesizing-Light-Field-Video-from-Monocular-Video
StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation
Motion Transformer for Unsupervised Image Animation
- Paper:
- Code: https://github.com/JialeTao/MoTrans
Sound-Guided Semantic Video Generation
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/anonymous5584/sound-guided-semantic-video-generation
Layered Controllable Video Generation
Diverse Generation from a Single Video Made Possible
Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation
EAGAN: Efficient Two-Stage Evolutionary Architecture Search for GANs
BlobGAN: Spatially Disentangled Scene Representations
Others
Learning Local Implicit Fourier Representation for Image Warping
- Paper: https://ipl.dgist.ac.kr/LTEW.pdf
- Code: https://github.com/jaewon-lee-b/ltew
- Tags: Image Warping
Dress Code: High-Resolution Multi-Category Virtual Try-On
- Paper: https://arxiv.org/abs/2204.08532
- Code: https://github.com/aimagelab/dress-code
- Tags: Virtual Try-On
High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions
- Paper: https://arxiv.org/abs/2206.14180
- Code: https://github.com/sangyun884/HR-VITON
- Tags: Virtual Try-On
Single Stage Virtual Try-on via Deformable Attention Flows
- Paper: https://arxiv.org/abs/2207.09161
- Tags: Virtual Try-On
Outpainting by Queries
- Paper: https://arxiv.org/abs/2207.05312
- Code: https://github.com/Kaiseem/QueryOTR
- Tags: Outpainting
Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal
- Paper: https://arxiv.org/abs/2207.08178
- Code: https://github.com/thinwayliu/Watermark-Vaccine
- Tags: Watermark Protection
Efficient Meta-Tuning for Content-aware Neural Video Delivery
- Paper: https://arxiv.org/abs/2207.09691
- Code: https://github.com/Neural-video-delivery/EMT-Pytorch-ECCV2022
- Tags: Video Delivery
Human-centric Image Cropping with Partition-aware and Content-preserving Features
CelebV-HQ: A Large-Scale Video Facial Attributes Dataset
- Paper: https://arxiv.org/abs/2207.12393
- Code: https://github.com/CelebV-HQ/CelebV-HQ
- Tags: Dataset
Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis
- Paper: https://arxiv.org/abs/2207.11770
- Code: https://github.com/sstzal/DFRF
- Tags: Talking Head Synthesis
Responsive Listening Head Generation: A Benchmark Dataset and Baseline
Contrastive Monotonic Pixel-Level Modulation
AutoTransition: Learning to Recommend Video Transition Effects
Bringing Rolling Shutter Images Alive with Dual Reversed Distortion
Learning Object Placement via Dual-path Graph Completion
DeepMCBM: A Deep Moving-camera Background Model
Mind the Gap in Distilling StyleGANs
StyleSwap: Style-Based Generator Empowers Robust Face Swapping
- Paper: https://arxiv.org/abs/2209.13514
- Code: https://github.com/Seanseattle/StyleSwap
- Tags: Face Swapping
Geometric Representation Learning for Document Image Rectification
- Paper: ECVA | European Computer Vision Association
- Code: https://github.com/fh2019ustc/DocGeoNet
- Tags: Document Image Rectification
Studying Bias in GANs through the Lens of Race
- Paper: ECVA | European Computer Vision Association
- Tags: Racial Bias
On the Robustness of Quality Measures for GANs
- Paper: https://arxiv.org/abs/2201.13019
- Code: https://github.com/MotasemAlfarra/R-FID-Robustness-of-Quality-Measures-for-GANs
TREND: Truncated Generalized Normal Density Estimation of Inception Embeddings for GAN Evaluation
- Paper: ECVA | European Computer Vision Association
- Tags: GAN Evaluation
AAAI2022-Low-Level-Vision
Image Restoration - 图像恢复
Unsupervised Underwater Image Restoration: From a Homology Perspective
- Paper: AAAI2022: Unsupervised Underwater Image Restoration: From a Homology Perspective
- Tags: Underwater Image Restoration
Panini-Net: GAN Prior based Degradation-Aware Feature Interpolation for Face Restoration
- Paper: AAAI2022: Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration
- Code: GitHub - wyhuai/Panini-Net: [AAAI 2022] Panini-Net: GAN Prior based Degradation-Aware Feature Interpolation for Face Restoration
- Tags: Face Restoration
Burst Restoration
Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers
- Paper: AAAI2022: SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers
- Code: https://github.com/laulampaul/siamtrans
Video Restoration
Transcoded Video Restoration by Temporal Spatial Auxiliary Network
- Paper: AAAI2022: Transcoded Video Restoration by Temporal Spatial Auxiliary Network
- Tags: Transcoded Video Restoration
Super Resolution - 超分辨率
Image Super Resolution
SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution
Efficient Non-Local Contrastive Attention for Image Super-Resolution
- Paper: https://arxiv.org/abs/2201.03794
- Code: GitHub - Zj-BinXia/ENLCA: This project is official implementation of 'Efficient Non-Local Contrastive Attention for Image Super-Resolution', AAAI2022
Best-Buddy GANs for Highly Detailed Image Super-Resolution
Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
- Paper: AAAI2022: Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
- Tags: Text SR
Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-Based Super-Resolution
- Paper: AAAI2022: Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-Based Super-Resolution
- Code: GitHub - Zj-BinXia/AMSA: This project is the official implementation of 'Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution', AAAI2022
- Tags: Reference-Based SR
Detail-Preserving Transformer for Light Field Image Super-Resolution
- Paper: AAAI2022: Detail-Preserving Transformer for Light Field Image Super-Resolution
- Tags: Light Field
Denoising - 去噪
Image Denoising
Generative Adaptive Convolutions for Real-World Noisy Image Denoising
Video Denoising
ReMoNet: Recurrent Multi-Output Network for Efficient Video Denoising
Deblurring - 去模糊
Video Deblurring
Deep Recurrent Neural Network with Multi-Scale Bi-Directional Propagation for Video Deblurring
Deraining - 去雨
Online-Updated High-Order Collaborative Networks for Single Image Deraining
Close the Loop: A Unified Bottom-up and Top-down Paradigm for Joint Image Deraining and Segmentation
- Paper: AAAI2022: Close the Loop: A Unified Bottom-up and Top-down Paradigm for Joint Image Deraining and Segmentation
- Tags: Joint Image Deraining and Segmentation
Dehazing - 去雾
Uncertainty-Driven Dehazing Network
Demosaicing - 去马赛克
Deep Spatial Adaptive Network for Real Image Demosaicing
HDR Imaging / Multi-Exposure Image Fusion - HDR图像生成 / 多曝光图像融合
TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework Using Self-Supervised Multi-Task Learning
Image Enhancement - 图像增强
Low-Light Image Enhancement
Low-Light Image Enhancement with Normalizing Flow
Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement
Semantically Contrastive Learning for Low-Light Image Enhancement
- Paper: AAAI2022: Semantically Contrastive Learning for Low-Light Image Enhancement
- Tags: contrastive learning
Image Matting - 图像抠图
MODNet: Trimap-Free Portrait Matting in Real Time
Shadow Removal - 阴影消除
Efficient Model-Driven Network for Shadow Removal
Image Compression - 图像压缩
Towards End-to-End Image Compression and Analysis with Transformers
- Paper: https://arxiv.org/abs/2112.09300
- Code: https://github.com/BYchao100/Towards-Image-Compression-and-Analysis-with-Transformers
- Tags: Transformer
OoDHDR-Codec: Out-of-Distribution Generalization for HDR Image Compression
Two-Stage Octave Residual Network for End-to-End Image Compression
Image Quality Assessment - 图像质量评价
Content-Variant Reference Image Quality Assessment via Knowledge Distillation
Perceptual Quality Assessment of Omnidirectional Images
- Paper: AAAI2022: Perceptual Quality Assessment of Omnidirectional Images
- Tags: Omnidirectional Images
Style Transfer - 风格迁移
Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization
- Paper: https://arxiv.org/abs/2103.11784
- Code: GitHub - czczup/URST: [AAAI 2022] Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization
Deep Translation Prior: Test-Time Training for Photorealistic Style Transfer
Image Editing - 图像编辑
Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换
SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal
- Paper: AAAI2022: SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal
- Code: https://github.com/Snowfallingplum/SSAT
- Tags: Makeup Transfer and Removal
Assessing a Single Image in Reference-Guided Image Synthesis
Interactive Image Generation with Natural-Language Feedback
PetsGAN: Rethinking Priors for Single Image Generation
Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction
- Paper: AAAI2022: Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction
Hierarchical Image Generation via Transformer-Based Sequential Patch Selection
Style-Guided and Disentangled Representation for Robust Image-to-Image Translation
OA-FSUI2IT: A Novel Few-Shot Cross Domain Object Detection Framework with Object-Aware Few-shot Unsupervised Image-to-Image Translation
- Paper: AAAI2022: OA-FSUI2IT: A Novel Few-Shot Cross Domain Object Detection Framework with Object-Aware Few-shot Unsupervised Image-to-Image Translation
- Code: https://github.com/emdata-ailab/FSCD-Det
- Tags: Image-to-Image Translation used for Object Detection
Video Generation
Learning Temporally and Semantically Consistent Unpaired Video-to-Video Translation through Pseudo-Supervision from Synthetic Optical Flow
- Paper: AAAI2022: Learning Temporally and Semantically Consistent Unpaired Video-to-Video Translation through Pseudo-Supervision from Synthetic Optical Flow
- Code: GitHub - wangkaihong/Unsup_Recycle_GAN: Code for "Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow", AAAI 2022
参考
什么是low-level、high-level任务_low-level任务_WTHunt的博客-CSDN博客