CVPR2020论文开源项目合集
Exploring Self-attention for Image Recognition
| 1 | 论文：https://hszhao.github.io/papers/cvpr20_san.pdf |
Improving Convolutional Networks with Self-Calibrated Convolutions
| 1 | 主页：https://mmcheng.net/scconv/ |
Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets
| 1 | 论文：https://arxiv.org/abs/2003.13549 |
图像分类
Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion
| 1 | 论文：https://arxiv.org/abs/2003.04490 |
Spatially Attentive Output Layer for Image Classification
| 1 | 论文：https://arxiv.org/abs/2004.07570 |
目标检测
Dynamic Refinement Network for Oriented and Densely Packed Object Detection
| 1 | 论文：https://arxiv.org/abs/2005.09973 |
Scale-Equalizing Pyramid Convolution for Object Detection
| 1 | 论文：https://arxiv.org/abs/2005.03101 |
Revisiting the Sibling Head in Object Detector
| 1 | 论文：https://arxiv.org/abs/2003.07540 |
Scale-equalizing Pyramid Convolution for Object Detection
| 1 | 论文：暂无 |
Detection in Crowded Scenes: One Proposal, Multiple Predictions
| 1 | 论文：https://arxiv.org/abs/2003.09163 |
Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection
| 1 | 论文：https://arxiv.org/abs/2004.04725 |
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
| 1 | 论文：https://arxiv.org/abs/1912.02424 |
BiDet: An Efficient Binarized Object Detector
| 1 | 论文：https://arxiv.org/abs/2003.03961 |
Harmonizing Transferability and Discriminability for Adapting Object Detectors
| 1 | 论文：https://arxiv.org/abs/2003.06297 |
CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
| 1 | 论文：https://arxiv.org/abs/2003.09119 |
Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
| 1 | 论文：https://arxiv.org/abs/2003.11818 |
EfficientDet: Scalable and Efficient Object Detection
| 1 | 论文：https://arxiv.org/abs/1911.09070 |
3D目标检测
Train in Germany, Test in The USA: Making 3D Object Detectors Generalize
| 1 | 论文：https://arxiv.org/abs/2005.08139 |
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
| 1 | 论文：https://arxiv.org/abs/2004.05679 |
3DSSD: Point-based 3D Single Stage Object Detector
| 1 | 论文：https://arxiv.org/abs/2002.10187 |
Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
| 1 | 论文：https://arxiv.org/abs/2004.03572 |
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
| 1 | 论文：https://arxiv.org/abs/2004.03080 |
DSGN: Deep Stereo Geometry Network for 3D Object Detection
| 1 | 论文：https://arxiv.org/abs/2001.03398 |
LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
| 1 | 论文：https://arxiv.org/abs/2004.01389 |
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
| 1 | 论文：https://arxiv.org/abs/1912.13192 |
Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
| 1 | 论文：https://arxiv.org/abs/2003.01251 |
视频目标检测
Memory Enhanced Global-Local Aggregation for Video Object Detection
| 1 | 论文：https://arxiv.org/abs/2003.12063 |
目标跟踪
D3S – A Discriminative Single Shot Segmentation Tracker
| 1 | 论文：https://arxiv.org/abs/1911.08862 |
ROAM: Recurrently Optimizing Tracking Model
| 1 | 论文：https://arxiv.org/abs/1907.12006 |
Siam R-CNN: Visual Tracking by Re-Detection
| 1 | 主页：https://www.vision.rwth-aachen.de/page/siamrcnn |
Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises
| 1 | 论文：https://arxiv.org/abs/2003.09595 |
High-Performance Long-Term Tracking with Meta-Updater
| 1 | 论文：https://arxiv.org/abs/2004.00305 |
AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization
| 1 | 论文：https://arxiv.org/abs/2003.12949 |
Probabilistic Regression for Visual Tracking
| 1 | 论文：https://arxiv.org/abs/2003.12565 |
MAST: A Memory-Augmented Self-supervised Tracker
| 1 | 论文：https://arxiv.org/abs/2002.07793 |
Siamese Box Adaptive Network for Visual Tracking
| 1 | 论文：https://arxiv.org/abs/2003.06761 |
语义分割
Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation
| 1 | 论文：暂无 |
Single-Stage Semantic Segmentation from Image Labels
| 1 | 论文：https://arxiv.org/abs/2005.08104 |
Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
| 1 | 论文：https://arxiv.org/abs/2003.00867 |
MSeg: A Composite Dataset for Multi-domain Semantic Segmentation
| 1 | 论文：http://vladlen.info/papers/MSeg.pdf |
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
| 1 | 论文：https://arxiv.org/abs/2005.02551 |
Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
| 1 | 论文：https://arxiv.org/abs/2004.07703 |
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation
| 1 | 论文：https://arxiv.org/abs/2004.04581 |
Temporally Distributed Networks for Fast Video Segmentation
| 1 | 论文：https://arxiv.org/abs/2004.01800 |
Context Prior for Scene Segmentation
| 1 | 论文：https://arxiv.org/abs/2004.01547 |
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
| 1 | 论文：https://arxiv.org/abs/2003.13328 |
Cars Can’t Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks
| 1 | 论文：https://arxiv.org/abs/2003.05128 |
Learning Dynamic Routing for Semantic Segmentation
| 1 | 论文：https://arxiv.org/abs/2003.10401 |
实例分割
PolarMask: Single Shot Instance Segmentation with Polar Representation
| 1 | 论文：https://arxiv.org/abs/1909.13226 |
CenterMask : Real-Time Anchor-Free Instance Segmentation
| 1 | 论文：https://arxiv.org/abs/1911.06667 |
BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
| 1 | 论文：https://arxiv.org/abs/2001.00309 |
Deep Snake for Real-Time Instance Segmentation
| 1 | 论文：https://arxiv.org/abs/2001.01629 |
Mask Encoding for Single Shot Instance Segmentation
| 1 | 论文：https://arxiv.org/abs/2003.11712 |
全景分割
Pixel Consensus Voting for Panoptic Segmentation
| 1 | 论文：https://arxiv.org/abs/2004.01849 |
BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation
| 1 | 论文：https://arxiv.org/abs/2003.14031 |
视频目标分割
A Transductive Approach for Video Object Segmentation
| 1 | 论文：https://arxiv.org/abs/2004.07193 |
State-Aware Tracker for Real-Time Video Object Segmentation
| 1 | 论文：https://arxiv.org/abs/2003.00482 |
Learning Fast and Robust Target Models for Video Object Segmentation
| 1 | 论文：https://arxiv.org/abs/2003.00908 |
Learning Video Object Segmentation from Unlabeled Videos
| 1 | 论文：https://arxiv.org/abs/2003.05020 |
超像素分割
Superpixel Segmentation with Fully Convolutional Networks
| 1 | 论文：https://arxiv.org/abs/2003.12929 |
NAS
AOWS: Adaptive and optimal network width search with latency constraints
| 1 | 论文：https://arxiv.org/abs/2005.10481 |
Densely Connected Search Space for More Flexible Neural Architecture Search
| 1 | 论文：https://arxiv.org/abs/1906.09607 |
MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
| 1 | 论文：https://arxiv.org/abs/2003.14058 |
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
| 1 | 论文下载链接：https://arxiv.org/abs/2004.05565 |
Neural Architecture Search for Lightweight Non-Local Networks
| 1 | 论文：https://arxiv.org/abs/2004.01961 |
Rethinking Performance Estimation in Neural Architecture Search
| 1 | 论文：https://arxiv.org/abs/2005.09917 |
CARS: Continuous Evolution for Efficient Neural Architecture Search
| 1 | 论文：https://arxiv.org/abs/1909.04977 |
GAN
Semantically Mutil-modal Image Synthesis
| 1 | 主页：http://seanseattle.github.io/SMIS |
Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping
| 1 | 论文：https://yiranran.github.io/files/CVPR2020_Unpaired%20Portrait%20Drawing%20Generation%20via%20Asymmetric%20Cycle%20Mapping.pdf |
Learning to Cartoonize Using White-box Cartoon Representations
| 1 | 论文：https://github.com/SystemErrorWang/White-box-Cartoonization/blob/master/paper/06791.pdf |
GAN Compression: Efficient Architectures for Interactive Conditional GANs
| 1 | 论文：https://arxiv.org/abs/2003.08936 |
Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions
| 1 | 论文：https://arxiv.org/abs/2003.01826 |
Re-ID
COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
| 1 | 论文：https://arxiv.org/abs/2005.07862 |
Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
| 1 | 论文：https://arxiv.org/abs/2004.04199 |
Pose-guided Visible Part Matching for Occluded Person ReID
| 1 | 论文：https://arxiv.org/abs/2004.00230 |
Weakly supervised discriminative feature learning with state information for person identification
| 1 | 论文：https://arxiv.org/abs/2002.11939 |
3D点云卷积
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
| 1 | 论文下载链接：https://arxiv.org/abs/2003.12971 |
FPConv: Learning Local Flattening for Point Convolution
| 1 | 论文：https://arxiv.org/abs/2002.10701 |
3D点云分类
PointAugment: an Auto-Augmentation Framework for Point Cloud Classification
| 1 | 论文：https://arxiv.org/abs/2002.10876 |
3D点云语义分割
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
| 1 | 论文：https://arxiv.org/abs/1911.11236 |
Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels
| 1 | 论文：https://arxiv.org/abs/2004.0409 |
PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
| 1 | 论文：https://arxiv.org/abs/2003.14032 |
Learning to Segment 3D Point Clouds in 2D Image Space
| 1 | 论文：https://arxiv.org/abs/2003.05593 |
3D点云实例分割
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
| 1 | 论文：https://arxiv.org/abs/2004.01658 |
3D点云配准
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
| 1 | 论文：https://arxiv.org/abs/2003.03164 |
RPM-Net: Robust Point Matching using Learned Features
| 1 | 论文：https://arxiv.org/abs/2003.13479 |
3D点云补全
Cascaded Refinement Network for Point Cloud Completion
| 1 | 论文：https://arxiv.org/abs/2004.03327 |
人脸识别
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
| 1 | 论文：https://arxiv.org/abs/2004.00288 |
Learning Meta Face Recognition in Unseen Domains
| 1 | 论文：https://arxiv.org/abs/2003.07733 |
人脸活体检测
Searching Central Difference Convolutional Networks for Face Anti-Spoofing
| 1 | 论文：https://arxiv.org/abs/2003.04092 |
人脸表情识别
Suppressing Uncertainties for Large-Scale Facial Expression Recognition
| 1 | 论文：https://arxiv.org/abs/2002.10392 |
人脸转正
Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images
| 1 | 论文：https://arxiv.org/abs/2003.08124 |
人脸3D重建
AvatarMe: Realistically Renderable 3D Facial Reconstruction “in-the-wild”
| 1 | 论文：https://arxiv.org/abs/2003.13845 |
FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction
| 1 | 论文：https://arxiv.org/abs/2003.13989 |
2D人体姿态估计
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
| 1 | 论文：https://arxiv.org/abs/1908.10357 |
The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
| 1 | 论文：https://arxiv.org/abs/1911.07524 |
Distribution-Aware Coordinate Representation for Human Pose Estimation
| 1 | 主页：https://ilovepose.github.io/coco/ |
3D人体姿态估计
Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach
| 1 | 主页：https://www.zhe-zhang.com/cvpr2020 |
Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data
| 1 | 论文下载链接：https://arxiv.org/abs/2004.01166 |
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis
| 1 | 主页：http://val.cds.iisc.ac.in/pgp-human/ |
Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation
| 1 | 论文：https://arxiv.org/abs/2004.00329 |
VIBE: Video Inference for Human Body Pose and Shape Estimation
| 1 | 论文：https://arxiv.org/abs/1912.05656 |
Back to the Future: Joint Aware Temporal Deep Learning 3D Human Pose Estimation
| 1 | 论文：https://arxiv.org/abs/2002.11251 |
Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
| 1 | 论文：https://arxiv.org/abs/2003.03972 |
人体解析
Correlating Edge, Pose with Parsing
| 1 | 论文：https://arxiv.org/abs/2005.01431 |
场景文本检测
UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
| 1 | 论文：https://arxiv.org/abs/2003.10608 |
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
| 1 | 论文：https://arxiv.org/abs/2002.10200 |
Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
| 1 | 论文：https://arxiv.org/abs/2003.07493 |
场景文本识别
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
| 1 | 论文：https://arxiv.org/abs/2005.10977 |
UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
| 1 | 论文：https://arxiv.org/abs/2003.10608 |
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
| 1 | 论文：https://arxiv.org/abs/2002.10200 |
Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition
| 1 | 论文：https://arxiv.org/abs/2003.06606 |
图像超分辨率
Structure-Preserving Super Resolution with Gradient Guidance
| 1 | 论文：https://arxiv.org/abs/2003.13081 |
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy
| 1 | 论文：https://arxiv.org/abs/2004.00448 |
视频超分辨率
Space-Time-Aware Multi-Resolution Video Enhancement
| 1 | 主页：https://alterzero.github.io/projects/STAR.html |
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
| 1 | 论文：https://arxiv.org/abs/2002.11616 |
模型压缩/剪枝
DMCP: Differentiable Markov Channel Pruning for Neural Networks
| 1 | 论文：https://arxiv.org/abs/2005.03354 |
Forward and Backward Information Retention for Accurate Binary Neural Networks
| 1 | 论文：https://arxiv.org/abs/1909.10788 |
Towards Efficient Model Compression via Learned Global Ranking
| 1 | 论文：https://arxiv.org/abs/1904.12368 |
HRank: Filter Pruning using High-Rank Feature Map
| 1 | 论文：http://arxiv.org/abs/2002.10179 |
GAN Compression: Efficient Architectures for Interactive Conditional GANs
| 1 | 论文：https://arxiv.org/abs/2003.08936 |
Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression
| 1 | 论文：https://arxiv.org/abs/2003.08935 |
视频理解/行为识别
Intra- and Inter-Action Understanding via Temporal Action Parsing
| 1 | 论文：https://arxiv.org/abs/2005.10229 |
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
| 1 | 论文：https://arxiv.org/abs/2005.05501 |
FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding
| 1 | 主页：https://sdolivia.github.io/FineGym/ |
TEA: Temporal Excitation and Aggregation for Action Recognition
| 1 | 论文：https://arxiv.org/abs/2004.01398 |
X3D: Expanding Architectures for Efficient Video Recognition
| 1 | 论文：https://arxiv.org/abs/2004.04730 |
Temporal Pyramid Network for Action Recognition
| 1 | 主页：https://decisionforce.github.io/TPN |
基于骨架的动作识别
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
| 1 | 论文：https://arxiv.org/abs/2003.14111 |
深度估计
Focus on defocus: bridging the synthetic to real domain gap for depth estimation
| 1 | 论文：https://arxiv.org/abs/2005.09623 |
Bi3D: Stereo Depth Estimation via Binary Classifications
| 1 | 论文：https://arxiv.org/abs/2005.07274 |
AANet: Adaptive Aggregation Network for Efficient Stereo Matching
| 1 | 论文：https://arxiv.org/abs/2004.09548 |
Towards Better Generalization: Joint Depth-Pose Learning without PoseNet
| 1 | 论文：https://github.com/B1ueber2y/TrianFlow |
单目深度估计
On the uncertainty of self-supervised monocular depth estimation
| 1 | 论文：https://arxiv.org/abs/2005.06209 |
3D Packing for Self-Supervised Monocular Depth Estimation
| 1 | 论文：https://arxiv.org/abs/1905.02693 |
Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
| 1 | 论文：https://arxiv.org/abs/2002.12114 |
6D目标姿态估计
MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion
| 1 | 论文：https://arxiv.org/abs/2004.04336 |
EPOS: Estimating 6D Pose of Objects with Symmetries
| 1 | 主页：http://cmp.felk.cvut.cz/epos |
G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
| 1 | 论文：https://arxiv.org/abs/2003.11089 |
手势估计
HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation
| 1 | 论文：https://arxiv.org/abs/2004.00060 |
Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data
| 1 | 论文：https://arxiv.org/abs/2003.09572 |
显著性检测
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection
| 1 | 论文：https://arxiv.org/abs/2004.08515 |
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
| 1 | 主页：http://dpfan.net/d3netbenchmark/ |
去噪
A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising
| 1 | 论文：https://arxiv.org/abs/2003.12751 |
CycleISP: Real Image Restoration via Improved Data Synthesis
| 1 | 论文：https://arxiv.org/abs/2003.07761 |
去雨
Multi-Scale Progressive Fusion Network for Single Image Deraining
| 1 | 论文：https://arxiv.org/abs/2003.10985 |
视频去模糊
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
| 1 | 主页：https://csbhr.github.io/projects/cdvd-tsp/index.html |
去雾
Multi-Scale Boosted Dehazing Network with Dense Feature Fusion
| 1 | 论文：https://arxiv.org/abs/2004.13388 |
特征点检测与描述
ASLFeat: Learning Local Features of Accurate Shape and Localization
| 1 | 论文：https://arxiv.org/abs/2003.10071 |
视觉问答(VQA)
VC R-CNN：Visual Commonsense R-CNN
| 1 | 论文：https://arxiv.org/abs/2002.12204 |
视频问答(VideoQA)
Hierarchical Conditional Relation Networks for Video Question Answering
| 1 | 论文：https://arxiv.org/abs/2002.10698 |
视觉语言导航
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
| 1 | 论文：https://arxiv.org/abs/2002.10638 |
视频压缩
Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement
| 1 | 论文：https://arxiv.org/abs/2003.01966 |
视频插值
Space-Time-Aware Multi-Resolution Video Enhancement
| 1 | 主页：https://alterzero.github.io/projects/STAR.html |
Scene-Adaptive Video Frame Interpolation via Meta-Learning
| 1 | 论文：https://arxiv.org/abs/2004.00779 |
Softmax Splatting for Video Frame Interpolation
| 1 | 主页：http://sniklaus.com/papers/softsplat |
风格迁移
Diversified Arbitrary Style Transfer via Deep Feature Perturbation
| 1 | 论文：https://arxiv.org/abs/1909.08223 |
Collaborative Distillation for Ultra-Resolution Universal Style Transfer
| 1 | 论文：https://arxiv.org/abs/2003.08436 |
车道线检测
Inter-Region Affinity Distillation for Road Marking Segmentation
| 1 | 论文：https://arxiv.org/abs/2004.05304 |
"人-物"交互(HOT)检测
Detailed 2D-3D Joint Representation for Human-Object Interaction
| 1 | 论文：https://arxiv.org/abs/2004.08154 |
Cascaded Human-Object Interaction Recognition
| 1 | 论文：https://arxiv.org/abs/2003.04262 |
VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions
| 1 | 论文：https://arxiv.org/abs/2003.05541 |
行人轨迹预测
Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction
| 1 | 论文：https://arxiv.org/abs/2002.11927 |
运动预测
Collaborative Motion Prediction via Neural Motion Message Passing
| 1 | 论文：https://arxiv.org/abs/2003.06594 |
MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird’s Eye View Maps
| 1 | 论文：https://arxiv.org/abs/2003.06754 |
虚拟试衣
Towards Photo-Realistic Virtual Try-On by Adaptively Generating?Preserving Image Content
| 1 | 论文：https://arxiv.org/abs/2003.05863 |
HDR
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
| 1 | 主页：https://www.cmlab.csie.ntu.edu.tw/~yulunliu/SingleHDR |
对抗样本
Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance
| 1 | 论文：https://arxiv.org/abs/1911.02466 |
语义场景补全
3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior
| 1 | 论文：https://arxiv.org/abs/2003.14052 |
数据集
Intra- and Inter-Action Understanding via Temporal Action Parsing
| 1 | 论文：https://arxiv.org/abs/2005.10229 |
Dynamic Refinement Network for Oriented and Densely Packed Object Detection
| 1 | 论文下载链接：https://arxiv.org/abs/2005.09973 |
COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
| 1 | 论文：https://arxiv.org/abs/2005.07862 |
KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
| 1 | 论文：https://arxiv.org/abs/2002.12687 |
MSeg: A Composite Dataset for Multi-domain Semantic Segmentation
| 1 | 论文：http://vladlen.info/papers/MSeg.pdf |
AvatarMe: Realistically Renderable 3D Facial Reconstruction “in-the-wild”
| 1 | 论文：https://arxiv.org/abs/2003.13845 |
Learning to Autofocus
| 1 | 论文：https://arxiv.org/abs/2004.12260 |
FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction
| 1 | 论文：https://arxiv.org/abs/2003.13989 |
Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data
| 1 | 论文下载链接：https://arxiv.org/abs/2004.01166 |
FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding
| 1 | 主页：https://sdolivia.github.io/FineGym/ |
A Local-to-Global Approach to Multi-modal Movie Scene Segmentation
| 1 | 主页：https://anyirao.com/projects/SceneSeg.html |
Deep Homography Estimation for Dynamic Scenes
| 1 | 论文：https://arxiv.org/abs/2004.02132 |
Assessing Image Quality Issues for Real-World Problems
| 1 | 主页：https://vizwiz.org/tasks-and-datasets/image-quality-issues/ |
UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
| 1 | 论文：https://arxiv.org/abs/2003.10608 |
PANDA: A Gigapixel-level Human-centric Video Dataset
| 1 | 论文：https://arxiv.org/abs/2003.04852 |
IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning
| 1 | 论文：https://arxiv.org/abs/2003.02920 |
Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
| 1 | 论文：https://arxiv.org/abs/2003.03972 |
其他
Equalization Loss for Long-Tailed Object Recognition
| 1 | 论文：https://arxiv.org/abs/2003.05176 |
Instance-aware Image Colorization
| 1 | 主页：https://ericsujw.github.io/InstColorization/ |
Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
| 1 | 论文：https://arxiv.org/abs/2005.09704 |
Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching
| 1 | 论文：https://arxiv.org/abs/2005.03860 |
Epipolar Transformers
| 1 | 论文：https://arxiv.org/abs/2005.04551 |
Bringing Old Photos Back to Life
| 1 | 主页：http://raywzy.com/Old_Photo/ |
MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
| 1 | 论文：https://arxiv.org/abs/2003.10955 |
Self-Supervised Viewpoint Learning from Image Collections
| 1 | 论文：https://arxiv.org/abs/2004.01793 |
Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations
| 1 | 论文：https://arxiv.org/abs/2003.12237 |
Towards Learning Structure via Consensus for Face Segmentation and Parsing
| 1 | 论文：https://arxiv.org/abs/1911.00957 |
Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging
| 1 | 论文：https://arxiv.org/abs/2003.13654 |
Lightweight Photometric Stereo for Facial Details Recovery
| 1 | 论文：https://arxiv.org/abs/2003.12307 |
Footprints and Free Space from a Single Color Image
| 1 | 论文：https://arxiv.org/abs/2004.06376 |
Self-Supervised Monocular Scene Flow Estimation
| 1 | 论文：https://arxiv.org/abs/2004.04143 |
Quasi-Newton Solver for Robust Non-Rigid Registration
| 1 | 论文：https://arxiv.org/abs/2004.04322 |
A Local-to-Global Approach to Multi-modal Movie Scene Segmentation
| 1 | 主页：https://anyirao.com/projects/SceneSeg.html |
DeepFLASH: An Efficient Network for Learning-based Medical Image Registration
| 1 | 论文：https://arxiv.org/abs/2004.02097 |
Self-Supervised Scene De-occlusion
| 1 | 主页：https://xiaohangzhan.github.io/projects/deocclusion/ |
Polarized Reflection Removal with Perfect Alignment in the Wild
| 1 | 主页：https://leichenyang.weebly.com/project-polarized.html |
Background Matting: The World is Your Green Screen
| 1 | 论文：https://arxiv.org/abs/2004.00626 |
What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective
| 1 | 论文：https://arxiv.org/abs/2003.11241 |
Look-into-Object: Self-supervised Structure Modeling for Object Recognition
| 1 | 论文：暂无 |
Video Object Grounding using Semantic Roles in Language Description
| 1 | 论文：https://arxiv.org/abs/2003.10606 |
Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives
| 1 | 论文：https://arxiv.org/abs/2003.10739 |
SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
| 1 | 论文：http://www.cs.umd.edu/~yuejiang/papers/SDFDiff.pdf |
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location
| 1 | 论文：https://arxiv.org/abs/2003.07064 |
GhostNet: More Features from Cheap Operations
| 1 | 论文：https://arxiv.org/abs/1911.11907 |
AdderNet: Do We Really Need Multiplications in Deep Learning?
| 1 | 论文：https://arxiv.org/abs/1912.13200 |
Deep Image Harmonization via Domain Verification
| 1 | 论文：https://arxiv.org/abs/1911.13239 |
Blurry Video Frame Interpolation
| 1 | 论文：https://arxiv.org/abs/2002.12259 |
Extremely Dense Point Correspondences using a Learned Feature Descriptor
| 1 | 论文：https://arxiv.org/abs/2003.00619 |
Filter Grafting for Deep Neural Networks
| 1 | 论文：https://arxiv.org/abs/2001.05868 |
Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
| 1 | 论文：https://arxiv.org/abs/2003.02824 |
Detecting Attended Visual Targets in Video
| 1 | 论文：https://arxiv.org/abs/2003.02501 |
Deep Image Spatial Transformation for Person Image Generation
| 1 | 论文：https://arxiv.org/abs/2003.00696 |
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications
| 1 | 论文：https://arxiv.org/abs/2003.01455 |
不确定中没中
FADNet: A Fast and Accurate Network for Disparity Estimation
| 1 | 论文：还没出来 |
https://github.com/rFID-submit/RandomFID：不确定中没中
https://github.com/JackSyu/AE-MSR：不确定中没中
https://github.com/fastconvnets/cvpr2020：不确定中没中
https://github.com/aimagelab/meshed-memory-transformer：不确定中没中
https://github.com/TWSFar/CRGNet：不确定中没中
https://github.com/CVPR-2020/CDARTS：不确定中没中
https://github.com/anucvml/ddn-cvprw2020：不确定中没中
https://github.com/dl-model-recommend/model-trust：不确定中没中
https://github.com/apratimbhattacharyya18/CVPR-2020-Corr-Prior：不确定中没中
https://github.com/onetcvpr/O-Net：不确定中没中
https://github.com/502463708/Microcalcification_Detection：不确定中没中
https://github.com/anonymous-for-review/cvpr-2020-deep-smoke-machine：不确定中没中
https://github.com/anonymous-for-review/cvpr-2020-smoke-recognition-dataset：不确定中没中
https://github.com/cvpr-nonrigid/dataset：不确定中没中
https://github.com/theFool32/PPBA：不确定中没中
https://github.com/Realtime-Action-Recognition/Realtime-Action-Recognition
842
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
