ICCV2021|底层视觉(图像生成,图像编辑,超分辨率等)相关论文汇总(附论文链接/代码)[持续更新]

ICCV2021|底层视觉和图像生成相关论文汇总(如果觉得有帮助,欢迎点赞和收藏)

A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation

整理汇总下2021年ICCV中图像生成(Image Generation)和底层视觉(Low-Level Vision)任务相关的论文和代码,包括图像生成,图像编辑,图像风格迁移,图像翻译,图像修复,图像超分及其他底层视觉任务。大家如果觉得有帮助,欢迎点赞和收藏~~

优先在Github更新:Awesome-ICCV2021-Low-Level-Vision,欢迎star~
知乎:https://zhuanlan.zhihu.com/p/412822286
参考或转载请注明出处

ICCV2021官网:https://iccv2021.thecvf.com/

ICCV2021完整论文列表:https://openaccess.thecvf.com/ICCV2021

开会时间:2021年10月11日-10月17日

【Contents】

1.图像生成(Image Generation)

Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts

  • Paper:https://arxiv.org/abs/2104.00887
  • Code:https://github.com/clovaai/mxfont
  • 小样本字体生成

PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering

  • Code:https://github.com/RenYurui/PIRender

Toward Spatially Unbiased Generative Models

  • Code:https://github.com/jychoi118/toward_spatial_unbiased

Disentangled Lifespan Face Synthesis

  • Paper:https://arxiv.org/abs/2108.02874
  • Code:https://github.com/clovaai/mxfont

Handwriting Transformers

  • Paper:https://arxiv.org/abs/2104.03964
  • Code:https://github.com/ankanbhunia/Handwriting-Transformers

Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation

  • Paper:https://arxiv.org/abs/2103.16146

ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement

  • Paper:https://arxiv.org/abs/2104.02699
  • Code:https://github.com/yuval-alaluf/restyle-encoder

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction

  • Paper:https://arxiv.org/abs/2108.03798
  • Code:https://github.com/huage001/painttransformer

GAN Inversion for Out-of-Range Images with Geometric Transformations

  • Paper:https://arxiv.org/abs/2108.08998

The Animation Transformer: Visual Correspondence via Segment Matching

  • Paper:https://arxiv.org/abs/2109.02614
  • 手绘图变动画

Image Synthesis via Semantic Composition

  • Paper:https://shepnerd.github.io/scg/resources/01145.pdf
  • Code:https://github.com/dvlab-research/SCGAN

2.图像编辑(Image Manipulation/Image Editing)

EigenGAN: Layer-Wise Eigen-Learning for GANs

  • Paper:https://arxiv.org/abs/2104.12476
  • Code:https://github.com/LynnHo/EigenGAN-Tensorflow

From Continuity to Editability: Inverting GANs with Consecutive Images

  • Paper:https://arxiv.org/abs/2107.13812
  • Code:https://github.com/cnnlstm/InvertingGANs_with_ConsecutiveImgs

HeadGAN: One-shot Neural Head Synthesis and Editing

  • Paper:https://arxiv.org/abs/2012.08261

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

  • Code:https://github.com/csyxwei/OroJaR

Sketch Your Own GAN

  • Paper:https://arxiv.org/abs/2108.02774
  • Code:https://github.com/PeterWang512/GANSketching

A Latent Transformer for Disentangled Face Editing in Images and Videos

  • Paper:https://arxiv.org/abs/2106.11895
  • Code:https://github.com/InterDigitalInc/Latent-Transformer

Learning Facial Representations from the Cycle-consistency of Face

  • Paper:https://arxiv.org/abs/2108.03427
  • Code:https://github.com/jiarenchang/facecycle

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

  • Paper:https://arxiv.org/abs/2103.17249
  • Code:https://github.com/orpatashnik/StyleCLIP

Talk-to-Edit: Fine-Grained Facial Editing via Dialog

  • Paper:https://arxiv.org/abs/2109.04425
  • Code:https://github.com/yumingj/Talk-to-Edit

Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing

  • Paper:https://cuiaiyu.github.io/dressing-in-order/Cui_Dressing_in_Order.pdf
  • Code:https://github.com/cuiaiyu/dressing-in-order

3.图像风格迁移(Image Transfer)

ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity

  • Paper:https://arxiv.org/abs/2103.09776

Domain Aware Universal Style Transfer

  • Paper:https://arxiv.org/abs/2108.04441
  • Code:https://github.com/Kibeom-Hong/Domain-Aware-Style-Transfer

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

  • Paper:https://arxiv.org/abs/2108.03647
  • Code:https://github.com/Huage001/AdaAttN

4.图像翻译(Image to Image Translation)

SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation

  • Paper:https://arxiv.org/abs/2103.16219
  • Code:https://github.com/NetEase-GameAI/SPatchGAN

Scaling-up Disentanglement for Image Translation

  • Paper:https://arxiv.org/abs/2103.14017
  • Code:https://github.com/avivga/overlord

5.图像修复(Image Inpaiting/Image Completion)

Implicit Internal Video Inpainting

  • Code:https://github.com/Tengfei-Wang/Implicit-Internal-Video-Inpainting

Internal Video Inpainting by Implicit Long-range Propagation

  • Code:https://github.com/Tengfei-Wang/Annotated-4K-Videos

Occlusion-Aware Video Object Inpainting

  • Paper:https://arxiv.org/abs/2108.06765

High-Fidelity Pluralistic Image Completion with Transformers

  • Paper:https://arxiv.org/abs/2103.14031
  • Code:https://github.com/raywzy/ICT

Image Inpainting via Conditional Texture and Structure Dual Generation

  • Paper:https://arxiv.org/abs/2108.09760v1
  • Code:https://github.com/Xiefan-Guo/CTSDG

CR-Fill: Generative Image Inpainting with Auxiliary Contextual Reconstruction

  • Paper:https://arxiv.org/abs/2011.12836
  • Code:https://github.com/zengxianyu/crfill

6.图像超分辨率(Image Super-Resolution)

Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution

  • Code:https://github.com/JingyunLiang/MANet

Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling

  • Code:https://github.com/JingyunLiang/HCFlow

Deep Blind Video Super-resolution

  • Code:https://github.com/csbhr/Deep-Blind-VSR

Omniscient Video Super-Resolution

  • Code:https://github.com/psychopa4/OVSR

Learning A Single Network for Scale-Arbitrary Super-Resolution

  • Paper:https://arxiv.org/abs/2004.03791
  • Code:https://github.com/LongguangWang/ArbSR

Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

  • Paper:https://arxiv.org/abs/2108.08286

Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts

  • Paper:https://arxiv.org/abs/2104.06191

Attention-Based Multi-Reference Learning for Image Super-Resolution

  • Paper:https://openaccess.thecvf.com/content/ICCV2021/papers/Pesavento_Attention-Based_Multi-Reference_Learning_for_Image_Super-Resolution_ICCV_2021_paper.pdf

7.图像去雨(Image Deraining)

Structure-Preserving Deraining with Residue Channel Prior Guidance

  • Code:https://github.com/Joyies/SPDNet

8.图像去雾(Image Dehazing)

9.去模糊(Deblurring)

Bringing Events into Video Deblurring with Non consecutively Blurry Frames

  • Code:https://github.com/shangwei5/D2Net

Rethinking Coarse-to-Fine Approach in Single Image Deblurring

  • Paper:https://arxiv.org/abs/2108.05054
  • Code:https://github.com/chosj95/MIMO-UNet

Bringing Events into Video Deblurring with Non consecutively Blurry Frames

  • Code:https://github.com/shangwei5/D2Net

10.去噪(Denoising)

C2N: Practical Generative Noise Modeling for Real-World Denoising

  • Paper:https://openaccess.thecvf.com/content/ICCV2021/papers/Jang_C2N_Practical_Generative_Noise_Modeling_for_Real-World_Denoising_ICCV_2021_paper.pdf

11.图像恢复(Image Restoration)

Spatially-Adaptive Image Restoration using Distortion-Guided Networks

  • Paper:https://arxiv.org/abs/2108.08617

Dynamic Attentive Graph Learning for Image Restoration

  • Paper:https://arxiv.org/abs/2109.06620
  • Code:https://github.com/jianzhangcs/DAGL

12.图像增强(Image Enhancement)

StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement

  • Paper:https://arxiv.org/abs/2107.12898
  • Code:https://github.com/IDKiro/StarEnhancer

Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables

  • Paper:https://arxiv.org/abs/2108.08697

13.图像质量评价(Image Quality Assessment)

MUSIQ: Multi-scale Image Quality Transformer

  • Paper:https://arxiv.org/abs/2108.05997

14.插帧(Frame Interpolation)

XVFI: eXtreme Video Frame Interpolation

  • Paper:https://arxiv.org/abs/2103.16206
  • Code:https://github.com/JihyongOh/XVFI

Asymmetric Bilateral Motion Estimation for Video Frame Interpolation

  • Paper: https://arxiv.org/abs/2108.06815
  • Code: https://github.com/JunHeum/ABME

15.视频/图像压缩(Video/Image Compression)

Extending Neural P-frame Codecs for B-frame Coding

  • Paper:https://arxiv.org/abs/2104.00531

Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform

  • Paper:https://arxiv.org/abs/2108.09551
  • Code:https://github.com/micmic123/QmapCompression

16.其他底层视觉任务(Other Low Level Vision)

Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation

  • Code:https://github.com/Anonymous-iccv2021-paper3163/CaFM-Pytorch
  • 视频传输

Focal Frequency Loss for Image Reconstruction and Synthesis

  • Paper:https://arxiv.org/abs/2012.12821
  • Code:https://github.com/EndlessSora/focal-frequency-loss
  • 频域损失,补充空域损失的不足

ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss

  • Code:https://github.com/weitingchen83/ICCV2021-Single-Image-Desnowing-HDCWNet

IICNet: A Generic Framework for Reversible Image Conversion

  • Code:https://github.com/felixcheng97/IICNet

Self-Conditioned Probabilistic Learning of Video Rescaling

  • Paper:https://arxiv.org/abs/2107.11639

HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset

  • Paper:https://arxiv.org/abs/2103.14943
  • Code:https://github.com/guanyingc/DeepHDRVideo

A New Journey from SDRTV to HDRTV

  • Paper:https://arxiv.org/abs/2108.07978
  • Code:https://github.com/chxy95/HDRTVNet

SSH: A Self-Supervised Framework for Image Harmonization

  • Paper:https://arxiv.org/abs/2108.06805
  • Code:https://github.com/VITA-Group/SSHarmonization

Towards Vivid and Diverse Image Colorization with Generative Color Prior

  • Paper:https://arxiv.org/abs/2108.08826

Towards Flexible Blind JPEG Artifacts Removal

  • Paper:https://github.com/jiaxi-jiang/FBCNN/releases/download/v1.0/FBCNN_ICCV2021.pdf
  • Code:https://github.com/jiaxi-jiang/FBCNN
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值