☪️论文下载:https://pan.baidu.com/share/init?surl=gjfUQlPf73MCk4vM8VbzoA
密码:aicv
🌟 CVPR 2021 持续更新最新论文/paper和相应的开源代码/code!
🚗 CVPR 2021 收录列表:http://cvpr2021.thecvf.com/sites/default/files/2021-03/accepted_paper_ids.txt
http://cvpr2021.thecvf.com/node/142
🚗 官网链接:http://cvpr2021.thecvf.com/
⏲️ 时间:2021年6月19日-6月25日 ⌚ 论文/paper接收公布时间:2021年2月28日
✋ 注:欢迎各位大佬提交issue,分享CVPR 2021论文/paper和开源项目!共同完善这个项目
✈️ 为了方便下载,已将论文/paper存储在文件夹中 ✔️ 表示论文/paper已下载 / Paper Download
CVPR 2021 论文/paper交流群已成立!已经收录的同学,可以添加微信:nvshenj125,请备注:CVPR+姓名+学校/公司名称!一定要根据格式申请,可以拉你进群。
【目录 可直接跳转】
【TODO】
✔️ Coordinate Attention for Efficient Mobile Network Design
解读: CA:新注意力机制
论文/paper:https://arxiv.org/abs/2103.02907
代码/code: https://github.com/Andrew-Qibin/CoordAttention
✔️Diverse Branch Block: Building a Convolution as an Inception-like Unit
解读:ACNet续作——CVPR2021:Diverse Branch Block
论文/paper: https://arxiv.org/abs/2103.13425
代码/code: https://github.com/DingXiaoH/DiverseBranchBlock
✔️Involution: Inverting the Inherence of Convolution for Visual Recognition
论文/paper: https://arxiv.org/abs/2103.06255
代码/code: https://github.com/d-li14/involution
✔️ Inception Convolution with Efficient Dilation Search
论文/paper:https://arxiv.org/pdf/2012.13587.pdf
代码/code:https://github.com/yifan123/IC-Conv
✔️ RepVGG: Making VGG-style ConvNets Great Again
解读: RepVGG:极简架构,SOTA性能,让VGG式模型再次伟大| RepVGG-重参数化Backbone
论文/paper: https://arxiv.org/abs/2101.03697
代码/code: https://github.com/DingXiaoH/RepVGG
✔️ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network
解读:ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network 论文/paper学习
论文/paper: https://arxiv.org/abs/2007.00992
代码/code: https://github.com/clovaai/rexnet
✔️Scaling Local Self-Attention For Parameter Efficient Visual Backbones
论文/paper:https://arxiv.org/abs/2103.12731
代码/code:https://github.com/lucidrains/halonet-pytorch | 作者主页
✔️AttentiveNAS: Improving Neural Architecture Search via Attentive
论文/paper: https://arxiv.org/abs/2011.09011
代码/code:None
✔️Combined Depth Space based Architecture Search For Person Re-identification
论文/paper: https://arxiv.org/abs/2104.04163
代码/code:None
✔️Contrastive Neural Architecture Search with Neural Architecture Comparators
论文/paper: https://arxiv.org/abs/2103.05471
代码/code:https://github.com/chenyaofo/CTNAS
✔️DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation (CVPR 2021)
论文/paper:https://arxiv.org/abs/2103.15954
代码/code:None
✔️HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
论文/paper:https://arxiv.org/abs/2005.14446
代码/code:None
HR-NAS: Searching Efficient High-Resolution Neural Architectures with Transformers (CVPR2021)
论文/paper:None
代码/code:https://github.com/dingmyu/HR-NAS
✔️Inception Convolution with Efficient Dilation Search
论文/paper:https://arxiv.org/abs/2012.13587
代码/code:None
Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
论文/paper:None
代码/code: None
✔️Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search
论文/paper:https://arxiv.org/abs/2104.05309
代码/code: https://github.com/kcyu2014/nas-landmarkreg
✔️NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization
论文/paper:https://arxiv.org/abs/2104.00031 | 主页/Homepage
代码/code: None
✔️Neural Architecture Search with Random Labels
论文/paper:https://arxiv.org/abs/2101.11834
代码/code:https://github.com/megvii-model/RLNAS
✔️OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection
论文/paper:https://arxiv.org/abs/2103.04507
代码/code:https://github.com/VDIGPKU/OPANAS
✔️Prioritized Architecture Sampling with Monto-Carlo Tree Search
论文/paper:https://arxiv.org/abs/2103.11922
代码/code:https://github.com/xiusu/NAS-Bench-Macro
✔️ReNAS: Relativistic Evaluation of Neural Architecture Search
论文/paper:https://arxiv.org/abs/1910.01523
代码/code:None
✔️Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator
论文/paper:https://arxiv.org/abs/2103.07289
代码/code:https://github.com/eric8607242/SGNAS
✔️Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search
论文/paper:https://arxiv.org/abs/2101.11342
代码/code:None
✔️A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts
论文/paper:https://arxiv.org/abs/2105.00290
代码/code:None
✔️Binary Graph Neural Networks
论文/paper:https://arxiv.org/abs/2105.00290
代码/code:https://github.com/mbahri/binary_gnn
✔️Quantifying Explainers of Graph Neural Networks in Computational Pathology
论文/paper:https://arxiv.org/pdf/2011.12646.pdf
代码/code:https://github.com/histocartography/patho-quant-explainer
✔️Sequential Graph Convolutional Network for Active Learning
论文/paper:https://arxiv.org/pdf/2006.10219.pdf
代码/code:None
✔️Capsule Network is Not More Robust than Convolutional Network
论文/paper: https://arxiv.org/abs/2103.15459
代码/code:None
✔️Correlated Input-Dependent Label Noise in Large-Scale Image Classification (CVPR 2021 Oral)
论文/paper: https://arxiv.org/abs/2105.10305
代码/code:https://github.com/google/uncertainty-baselines/tree/master/baselines/imagenet
Adaptive Class Suppression Loss for Long-Tail Object Detection
论文/paper:https://arxiv.org/abs/2104.00885
代码/code:https://github.com/CASIA-IVA-Lab/ACSL
✔️Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
论文/paper: https://arxiv.org/abs/2104.06114
代码/code:https://github.com/cheng052/BRNet
✔️ Categorical Depth Distribution Network for Monocular 3D Object Detection
论文/paper: https://arxiv.org/abs/2103.01100
代码/code:https://github.com/TRAILab/CaDDN
✔️Center-based 3D Object Detection and Tracking
论文/paper:https://arxiv.org/abs/2006.11275
代码/code:https://github.com/tianweiy/CenterPoint
Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
论文/paper:https://arxiv.org/abs/2103.16368
代码/code:None
DAP: Detection-Aware Pre-training with Weak Supervision
论文/paper:https://arxiv.org/abs/2103.16651
代码/code:None
✔️Depth from Camera Motion and Object Detection
论文/paper:https://arxiv.org/abs/2103.01468
代码/code:https://github.com/griffbr/ODMD
✔️Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
论文/paper:https://arxiv.org/abs/2011.09670
代码/code:https://github.com/yangxue0827/RotationDetection
Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
论文/paper:https://arxiv.org/abs/2103.17115
代码/code:https://github.com/hzhupku/DCNet
✔️Distilling Object Detectors via Decoupled Features
论文/paper:https://arxiv.org/abs/2103.14475
代码/code:https://github.com/ggjy/DeFeat.pytorch
✔️ Dogfight: Detecting Drones from Drone Videos
论文/paper:https://arxiv.org/pdf/2103.17242
代码/code:None
✔️Domain-Specific Suppression for Adaptive Object Detection
论文/paper:https://arxiv.org/abs/2105.03570
代码/code:None
✔️End-to-End Object Detection with Fully Convolutional Network
论文/paper: https://arxiv.org/abs/2012.03544
代码/code: https://github.com/Megvii-BaseDetection/DeFCN
✔️FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
论文/paper:https://arxiv.org/abs/2103.05950
代码/code:https://github.com/MegviiDetection/FSCE
✔️General Instance Distillation for Object Detection
论文/paper:https://arxiv.org/abs/2103.02340
代码/code:None
✔️Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
解读:大白话 Generalized Focal Loss V2
论文/paper:https://arxiv.org/abs/2011.12885
代码/code:https://github.com/implus/GFocalV2
✔️GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
视频demo:https://www.youtube.com/watch?v=PWctKkyWrno
论文/paper:https://arxiv.org/abs/2103.17202
代码/code:https://github.com/abhi1kumar/groomed_nms
✔️Group Collaborative Learning for Co-Salient Object Detection
论文/paper:https://arxiv.org/abs/2104.01108
代码/code:https://github.com/fanq15/GCoNet
✔️I^3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object DetectorsNone
论文/paper:https://arxiv.org/abs/2103.13757
代码/code:None
Improved Handling of Motion Blur in Online Object Detection
论文/paper:https://arxiv.org/abs/2011.14448
代码/code:None
IQDet: Instance-wise Quality Distribution Sampling for Object Detection
论文/paper:https://arxiv.org/abs/2104.06936
代码/code:None
✔️Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework
论文/paper:https://arxiv.org/abs/2103.11402
代码/code:None
✔️Instance Localization for Self-supervised Detection Pretraining
论文/paper: https://arxiv.org/abs/2102.08318
代码/code:https://github.com/limbo0000/InstanceLoc
✔️MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
论文/paper: https://arxiv.org/abs/2103.04224
代码/code:None
✔️Multiple Instance Active Learning for Object Detection
论文/paper:https://github.com/yuantn/MIAL/raw/master/paper.pdf
代码/code:https://github.com/yuantn/MI-AOD
Line Segment Detection Using Transformers without Edges(CVPR 2021 Oral)
论文/paper: https://arxiv.org/abs/2101.01909
代码/code:None
Open-Vocabulary Object Detection Using Captions (CVPR 2021 Oral)
论文/paper: https://arxiv.org/abs/2011.10678
代码/code:None
✔️OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection
论文/paper: https://arxiv.org/abs/2103.04507
代码/code:https://github.com/VDIGPKU/OPANAS
✔️OTA: Optimal Transport Assignment for Object Detection
论文/paper:https://arxiv.org/abs/2103.14259
代码/code:https://github.com/Megvii-BaseDetection/OTA
Positive-Unlabeled Data Purification in the Wild for Object Detection
代码/code:None
PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery
论文/paper:https://arxiv.org/abs/2105.12990
代码/code:None
✔️Robust and Accurate Object Detection via Adversarial Learning
论文/paper:https://arxiv.org/abs/2103.13886
代码/code:None
✔️ReDet: A Rotation-equivariant Detector for Aerial Object Detection
论文/paper:https://arxiv.org/abs/2103.07733
代码/code:https://github.com/csuhan/ReDet
✔️Scale-aware Automatic Augmentation for Object Detection
论文/paper:https://arxiv.org/abs/2103.17220
代码/code: https://github.com/Jia-Research-Lab/SA-AutoAug
✔️Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection
论文/paper:https://arxiv.org/abs/2103.01903
代码/code:None
✔️Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
论文/paper:https://arxiv.org/abs/2011.12450
代码/code:https://github.com/PeizeSun/SparseR-CNN
✔️There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge
论文/paper:https://arxiv.org/abs/2103.01353
代码/code:http://rl.uni-freiburg.de/research/multimodal-distill
✔️Towards Open World Object Detection (CVPR 2021 Oarl)
论文/paper:https://arxiv.org/abs/2103.02603
代码/code:https://github.com/JosephKJ/OWOD
✔️Uncertainty-aware Joint Salient Object and Camouflaged Object Detection
论文/paper:https://arxiv.org/abs/2104.02628
代码/code:https://github.com/JingZhang617/Joint_COD_SOD
✔️UP-DETR: Unsupervised Pre-training for Object Detection with Transformers (CVPR2021 Oral)
解读:https://zhuanlan.zhihu.com/p/356349626 | 华南理工和微信AI提出的无监督预训练检测器UP-DETR
论文/paper: https://arxiv.org/abs/2011.09094
代码/code:https://github.com/dddzg/up-detr
✔️YOLOF:You Only Look One-level Feature
论文/paper:https://arxiv.org/abs/2103.09460
代码/code:https://github.com/megvii-model/YOLOF
✔️IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
论文/paper:https://arxiv.org/abs/2103.14938
代码/code:https://github.com/VISION-SJTU/IoUattack
✔️Graph Attention Tracking
论文/paper:https://arxiv.org/abs/2011.11204
代码/code:https://github.com/ohhhyeahhh/SiamGAT
✔️Learning a Proposal Classifier for Multiple Object Tracking
论文/paper:https://arxiv.org/abs/2103.07889
代码/code:https://github.com/daip13/LPC_MOT
✔️Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
论文/paper:https://arxiv.org/abs/2012.02337
代码/code:https://github.com/fatemeh-slh/ArTIST
✔️Rotation Equivariant Siamese Networks for Tracking
论文/paper: https://arxiv.org/abs/2012.13078
代码/code:https://github.com/dkgupta90/re-siamnet
✔️ Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
论文/paper:https://arxiv.org/pdf/2103.16746.pdf | Homepage
代码/code: https://github.com/wangxiao5791509/TNL2K_evaluation_toolkit
✔️Track to Detect and Segment: An Online Multi-Object Tracker
论文/paper:https://arxiv.org/pdf/2103.08808.pdf | 主页/Homepage
代码/code:https://github.com/JialianW/TraDeS
✔️Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking (CVPR 2021 Oral)
论文/paper:https://arxiv.org/abs/2103.11681
代码/code: https://github.com/594422814/TransformerTrack
✔️Transformer Tracking
论文/paper:https://arxiv.org/abs/2103.15436
代码/code: https://github.com/chenxin-dlut/TransT
✔️Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation
论文/paper:https://arxiv.org/abs/2103.08896 | 主页/Homepage
代码/code:https://github.com/jbeomlee93/AdvCAM
✔️A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation
论文/paper:https://arxiv.org/abs/2105.03186
代码/code:None
✔️ BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation
论文/paper:https://arxiv.org/abs/2103.08907
代码/code:https://github.com/jbeomlee93/BBAM
✔️Bidirectional Projection Network for Cross Dimension Scene Understanding (CVPR 2021 Oral)
论文/paper:https://arxiv.org/abs/2103.14326
代码/code:https://github.com/wbhu/BPNet
✔️Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
论文/paper:https://arxiv.org/abs/2103.16562 | 主页/Homepage
代码/codehttps://github.com/bowenc0221/boundary-iou-api
✔️Capturing Omni-Range Context for Omnidirectional Segmentation
论文/paper:https://arxiv.org/abs/2103.05687
代码/code:None | 作者主页/Homepage
✔️Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization
论文/paper:https://arxiv.org/abs/2103.13041
代码/code:None
✔️Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations
论文/paper:https://arxiv.org/abs/2103.06342
代码/code:None
✔️ Cross-Dataset Collaborative Learning for Semantic Segmentation
论文/paper:https://arxiv.org/abs/2103.11351
代码/code:None
✔️Cross-View Regularization for Domain Adaptive Panoptic Segmentation
论文/paper:https://arxiv.org/abs/2103.02584
代码/code:None
✔️Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
论文/paper: https://arxiv.org/abs/2011.10033
代码/code: https://github.com/xinge008/Cylinder3D
✔️DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation
论文/paper:https://arxiv.org/abs/2011.09876
代码/code:https://github.com/aliyun/DCT-Mask
✔️Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers
论文/paper:https://arxiv.org/abs/2103.12340
代码/code:https://github.com/lkeab/BCNet
✔️DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation(CVPR2021 Oral)
论文/paper:https://arxiv.org/abs/2103.15954
代码/code:None
✔️End-to-End Video Instance Segmentation with Transformers (CVPR2021 Oral)
论文/paper: https://arxiv.org/abs/2011.14503
代码/code:https://github.com/Epiphqny/VisTR
✔️FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space
论文/paper:https://arxiv.org/abs/2103.06030
代码/code:https://github.com/liuquande/FedDG-ELCFS
✔️ Fully Convolutional Networks for Panoptic Segmentation (CVPR2021 Oral)
论文/paper:https://arxiv.org/abs/2012.00720
代码/code:https://github.com/Jia-Research-Lab/PanopticFCN
✔️Incremental Few-Shot Instance Segmentation
论文/paper:https://arxiv.org/abs/2105.05312
代码/code:https://github.com/danganea/iMTFA
✔️Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild
解读:https://www.zhihu.com/question/446299297/answer/1769080299
论文/paper:https://arxiv.org/abs/2103.10391
代码/code:https://github.com/svip-lab/IVOS-W
✔️Learning Statistical Texture for Semantic Segmentation
论文/paper:https://arxiv.org/abs/2103.04133
代码/code: None
✔️Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation
论文/paper:https://arxiv.org/abs/2104.05239
代码/code: https://github.com/tinyalpha/BPR
✔️MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation
论文/paper:https://arxiv.org/abs/2103.05254
代码/code:None
✔️Multi-Scale Aligned Distillation for Low-Resolution Detection
论文/paper:https://jiaya.me/papers/ms_align_distill_cvpr21.pdf
代码/code:https://github.com/Jia-Research-Lab/MSAD
✔️Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
论文/paper:https://arxiv.org/abs/2103.04717
代码/code:None
✔️Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation
论文/paper: https://arxiv.org/abs/2103.14581
代码/code:None
✔️Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation
论文/paper:https://arxiv.org/abs/2103.14962
代码/code:https://github.com/edwardzhou130/Panoptic-PolarNet
✔️PLOP: Learning without Forgetting for Continual Semantic Segmentation
论文/paper:https://arxiv.org/abs/2011.11390
代码/code:https://github.com/arthurdouillard/CVPR2021_PLOP
✔️Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
论文/paper:https://arxiv.org/abs/2101.10979
代码/code:https://github.com/microsoft/ProDA
✔️RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
论文/paper:https://arxiv.org/abs/2104.08569
代码/code:https://github.com/zhanggang001/RefineMask/
✔️Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
论文/paper:https://arxiv.org/abs/2012.15840
代码/code:https://github.com/fudan-zvg/SETR
✔️RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening
论文/paper:https://arxiv.org/abs/2103.15597
代码/code:https://github.com/shachoi/RobustNet
✔️Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
论文/paper: https://arxiv.org/abs/2103.07074
代码/code:https://github.com/ShiQiu0419/BAAF-Net
✔️Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
解读:https://blog.csdn.net/msy1412/article/details/114938788
论文/paper: https://arxiv.org/abs/2103.04705
代码/code:None
✔️ SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation
视频demo:youtube
论文/paper:https://arxiv.org/abs/2103.10284
代码/code:https://github.com/goodproj13/SG-Net
✔️Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
论文/paper:http://arxiv.org/abs/2009.03137 | 主页 | Homepage
代码/code:https://github.com/QingyongHu/SensatUrban
Zero-Shot Instance Segmentation
解读:CVPR 2021 | 创新奇智首次提出零样本实例分割,助力解决工业场景数据瓶颈难题
论文/paper:None
代码/code:None
✔️Railroad Is Not a Train: Saliency As Pseudo-Pixel Supervision for Weakly Supervised Semantic Segmentation
论文/paper:https://arxiv.org/abs/2105.08965
代码/code:https://github.com/halbielee/EPS
✔️FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space
论文/paper:https://arxiv.org/abs/2103.06030
代码/code:https://github.com/liuquande/FedDG-ELCFS
✔️DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation
论文/paper:https://arxiv.org/abs/2103.15954
代码/code:None
✔️Learning Position and Target Consistency for Memory-based Video Object Segmentation
解读:论文翻译
论文/paper:https://arxiv.org/abs/2104.04329
代码/code:None
✔️SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation (CVPR 2021 Oral)
论文/paper:https://arxiv.org/abs/2101.08833
代码/code:https://github.com/dukebw/SSTVOS
✔️VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild
论文/paper:https://www.vspwdataset.com/CVPR2021__miao.pdf | 主页 / Homepage
代码/code:https://github.com/VSPW-dataset/VSPW_code
✔️Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild
解读:https://www.zhihu.com/question/446299297/answer/1769080299
论文/paper:https://arxiv.org/abs/2103.10391
代码/code:https://github.com/svip-lab/IVOS-W
✔️Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
视频/demo:https://hkchengrex.github.io/MiVOS/video.html#partb
论文/paper:https://arxiv.org/abs/2103.07941 | 主页/ Homepage
代码/code: https://github.com/hkchengrex/MiVOS
✔️End-to-End Human Object Interaction Detection with HOI Transformer
论文/paper: https://arxiv.org/abs/2103.04503
代码/code:https://github.com/bbepoch/HoiTransformer
✔️End-to-End Video Instance Segmentation with Transformers (CVPR2021 Oral)
论文/paper: https://arxiv.org/abs/2011.14503
代码/code:https://github.com/Epiphqny/VisTR
✔️HOTR: End-to-End Human-Object Interaction Detection with Transformers
论文/paper:https://arxiv.org/abs/2104.13682
代码/code:https://github.com/bbepoch/HoiTransformer
HR-NAS: Searching Efficient High-Resolution Neural Architectures with Transformers (CVPR 2021 Oral)
论文/paper:None | 报道
代码/code:https://github.com/dingmyu/HR-NAS
✔️Kaleido-BERT:Vision-Language Pre-training on Fashion Domain
视频讲解:http://dpfan.net/wp-content/uploads/Kaleido-BERT.mp4
论文/paper:https://arxiv.org/abs/2103.16110 | 中文版 / Chinese
代码/code: https://github.com/mczhuge/Kaleido-BERT
✔️LoFTR: Detector-Free Local Feature Matching with Transformers
论文/paper: https://arxiv.org/abs/2104.00680 | 主页 / Homepage
代码/code:https://github.com/zju3dv/LoFTR
✔️Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
视频/demo:youtube
论文/paper: https://arxiv.org/abs/2104.09224
代码/code: https://github.com/autonomousvision/transfuser
✔️MIST: Multiple Instance Spatial Transformer Network
论文/paper:https://arxiv.org/abs/1811.10725
代码/code:None
✔️ Multimodal Motion Prediction with Stacked Transformers
论文/paper:https://arxiv.org/pdf/2103.11624.pdf
代码/code:https://github.com/decisionforce/mmTransformer
✔️Pre-Trained Image Processing Transformer
论文/paper: https://arxiv.org/abs/2012.00364
代码/code:https://github.com/huawei-noah/Pretrained-IPT
✔️Pose Recognition with Cascade Transformers
论文/paper:https://arxiv.org/abs/2104.06976
代码/code:https://github.com/mlpc-ucsd/PRTR
✔️Revamping cross-modal recipe retrieval with hierarchical Transformers and self-supervised learning
代码/code:https://github.com/amzn/image-to-recipe-transformers
✔️Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
论文/paper:https://arxiv.org/abs/2012.15840
代码/code:https://github.com/fudan-zvg/SETR
✔️Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking (CVPR 2021 Oral)
论文/paper:https://arxiv.org/abs/2103.11681
代码/code: https://github.com/594422814/TransformerTrack
✔️Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
论文/paper: https://arxiv.org/abs/2103.16553
代码/code:None
✔️Transformer Tracking
论文/paper:https://arxiv.org/abs/2103.15436
代码/code: https://github.com/chenxin-dlut/TransT
✔️Transformer Interpretability Beyond Attention Visualization
论文/paper:https://arxiv.org/abs/2012.09838
代码/code:https://github.com/hila-chefer/Transformer-Explainability
✔️UP-DETR: Unsupervised Pre-training for Object Detection with Transformers (CVPR2021 Oral)
解读:https://zhuanlan.zhihu.com/p/356349626 | 华南理工和微信AI提出的无监督预训练检测器UP-DETR
论文/paper: https://arxiv.org/abs/2011.09094
代码/code:https://github.com/dddzg/up-detr
✔️Variational Transformer Networks for Layout Generation
论文/paper:https://arxiv.org/abs/2104.02416
代码/code:None
✔️A 3D GAN for Improved Large-pose Facial Recognition
论文/paper:https://arxiv.org/abs/2012.10545
代码/code:None
✔️ MagFace: A Universal Representation for Face Recognition and Quality Assessment (CVPR 2021 Oral)
论文/paper:https://arxiv.org/abs/2103.06627
代码/code:https://github.com/IrvingMeng/MagFace
✔️ WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
论文/paper:https://arxiv.org/abs/2103.04098 | 主页 | Homepage
代码/code:None
✔️ When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework(CVPR 2021 Oral)
论文/paper:https://arxiv.org/abs/2103.01520
代码/code:https://github.com/Hzzone/MTLFace
✔️ CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement
论文/paper:https://arxiv.org/abs/2103.07017
代码/code:None
✔️ HLA-Face: Joint High-Low Adaptation for Low Light Face Detection
解读:北京大学 | HLA-Face:用于暗光人脸检测的联合高-低自适应(CVPR2021
论文/paper: https://arxiv.org/abs/2104.01984 |主页 | Homepage
代码/code:https://github.com/daooshee/HLA-Face-Code
✔️ Cross Modal Focal Loss for RGBD Face Anti-Spoofing
解读:论文翻译 | CVPR2021 人脸防伪相关paper
论文/paper:https://arxiv.org/abs/2103.00948
代码/code:None
✔️ Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
论文/paper:https://arxiv.org/abs/2103.09096
代码/code:None
✔️ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
解读:CVPR 2021 Oral|商汤提出最新深伪评测基准 ForgeryNet:左右互搏——论火眼金睛的修炼
论文/paper:https://arxiv.org/abs/2103.05630 | 主页 | Homepage
代码/code:None
✔️ MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes
解读:Deepfake防御新思路有了!腾讯首次公开MagDR框架,已被AI顶会接收
论文/paper:https://arxiv.org/abs/2103.14211
代码/code:None
✔️ Multi-attentional Deepfake Detection (CVPR2021 preview)
论文/paper:https://arxiv.org/abs/2103.02406
代码/code:https://github.com/yoctta/multiple-attention
✔️Continuous Face Aging via Self-estimated Residual Age Embedding
论文/paper:https://arxiv.org/abs/2105.00020
代码/code:
✔️ PML: Progressive Margin Loss for Long-tailed Age Classification
论文/paper:https://arxiv.org/abs/2103.02140
代码/code:None
✔️ Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition
论文/paper:https://arxiv.org/abs/2103.13372
代码/code: None
✔️Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition
论文/paper:https://arxiv.org/abs/2104.05160 | 厦大新闻
代码/code: None
Learning Spatial-Semantic Relationship for Facial Attribute Recognition with Limited Labeled Data
论文/paper:None | 厦大新闻
代码/code: None
✔️Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video
论文/paper:https://arxiv.org/abs/2011.08627
代码/code:https://github.com/hongsukchoi/TCMR_RELEASE
✔️ Deep Dual Consecutive Network for Human Pose Estimation
视频demo:bilibil
论文/paper:https://arxiv.org/abs/2103.07254
代码/code:https://github.com/Pose-Group/DCPose
✔️HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation
论文/paper:https://arxiv.org/abs/2011.14672 | 主页/Homepage
代码/code: https://github.com/Jeff-sjtu/HybrIK
✔️Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors
视频demo:video
论文/paper:https://arxiv.org/abs/2103.17265
代码/code:| 主页/Homepage
✔️ Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks
论文/paper: https://arxiv.org/abs/2104.01797
代码/code:https://github.com/3dpose/3D-Multi-Person-Pose
✔️PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation(CVPR 2021 Oral)
论文/paper: https://arxiv.org/abs/2105.02465
代码/code:https://github.com/jfzhang95/PoseAug
✔️FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
论文/paper:https://arxiv.org/abs/2103.02242
代码/code: https://github.com/ethnhe/FFB6D
✔️FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism (CVPR2021 Oral)
论文/paper:https://arxiv.org/abs/2103.07054 | 主页 | Homepage
代码/code:https://github.com/DC1991/FS-Net
✔️GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation
论文/paper:http://arxiv.org/abs/2102.12145
代码/code:https://git.io/GDR-Net
✔️Camera-Space Hand Mesh Recovery via Semantic Aggregationand Adaptive 2D-1D Registration
论文/paper:https://arxiv.org/abs/2103.02845.pdf
代码/code:https://github.com/SeanChenxy/HandMesh
✔️Combined Depth Space based Architecture Search For Person Re-identification
论文/paper: https://arxiv.org/abs/2104.04163
代码/code:None
✔️Group-aware Label Transfer for Domain Adaptive Person Re-identification
论文/paper: https://arxiv.org/abs/2103.12366
代码/code:https://github.com/zkcys001/UDAStrongBaseline
✔️Intra-Inter Camera Similarity for Unsupervised Person Re-Identification
论文/paper: https://arxiv.org/abs/2103.11658
代码/code:https://github.com/SY-Xuan/IICS
✔️Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
论文/paper: https://arxiv.org/abs/2103.04618
代码/code:https://github.com/FlyingRoastDuck/MetaCam_DSCE
✔️Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
论文/paper:https://arxiv.org/abs/2012.00417
代码/code:https://github.com/HeliosZhao/M3L
✔️Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
论文/paper:https://arxiv.org/abs/2103.12462
代码/code:https://github.com/TPCD/LifelongReID
✔️Meta Batch-Instance Normalization for Generalizable Person Re-Identification
论文/paper: https://arxiv.org/abs/2011.14670
代码/code:https://github.com/bismex/MetaBIN
✔️Neural Feature Search for RGB-Infrared Person Re-Identification
论文/paper:https://arxiv.org/abs/2104.02366
代码/code:None
✔️Unsupervised Multi-Source Domain Adaptation for Person Re-Identification
论文/paper:https://arxiv.org/abs/2104.12961
代码/code:None
✔️Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification
论文/paper:https://arxiv.org/abs/2103.04337
代码/code:https://github.com/flysnowtiger/GRL
Coarse-To-Fine Person Re-Identification With Auxiliary-Domain Classification and Second-Order Information Bottleneck
论文/paper:None
代码/code:None
Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification
论文/paper:None
代码/code:None
Joint Generative and Contrastive Learning for Unsupervised Person Re-Identification
论文/paper:None
代码/code:None
BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification
论文/paper:None
代码/code:None
Person30K: A Dual-Meta Generalization Network for Person Re-Identification
论文/paper:None
代码/code:None
Diverse Part Discovery: Occluded Person Re-Identification With Part-Aware Transformer
论文/paper:None
代码/code:None
Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification
论文/paper:None
代码/code:None
Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
论文/paper:None
代码/code:None
Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification
论文/paper:None
代码/code:None
Partial Person Re-Identification With Part-Part Correspondence Learning
论文/paper:None
代码/code:None
Fine-Grained Shape-Appearance Mutual Learning for Cloth-Changing Person Re-Identification
论文/paper:None
代码/code:None
UnrealPerson: An Adaptive Pipeline Towards Costless Person Re-Identification
论文/paper:None
代码/code:None
Person Re-Identification Using Heterogeneous Local Graph Attention Networks
论文/paper:None
代码/code:None
Wide-Baseline Multi-Camera Calibration Using Person Re-Identification
论文/paper:None
代码/code:None
Unsupervised Pre-Training for Person Re-Identification
论文/paper:None
代码/code:None
Generalizable Person Re-Identification With Relevance-Aware Mixture of Experts
论文/paper:None
代码/code:None
✔️Anchor-Free Person Search
解读:https://zhuanlan.zhihu.com/p/359617800
论文/paper:https://arxiv.org/abs/2103.11617
代码/code:https://github.com/daodaofr/AlignPS
✔️Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
论文/paper:https://arxiv.org/abs/2012.04529
代码/code:https://github.com/chen-judge/RGBTCrowdCounting
✔️Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark
论文/paper:https://arxiv.org/abs/2105.02440
代码/code:https://github.com/VisDrone/DroneCrowd
✔️ Anycost GANs for Interactive Image Synthesis and Editing
视频/demo:youtube
论文/paper:https://arxiv.org/abs/2103.03243
代码/code:https://github.com/mit-han-lab/anycost-gan
✔️A 3D GAN for Improved Large-pose Facial Recognition
论文/paper:https://arxiv.org/abs/2012.10545
代码/code:None
✔️Closed-Form Factorization of Latent Semantics in GANs (CVPR 2021 Oral)
视频/demo:youtube
论文/paper:https://arxiv.org/abs/2007.06600 | 主页 | Homepage
代码/code:https://github.com/genforce/sefa
✔️ CoMoGAN: continuous model-guided image-to-image translation
论文/paper:https://arxiv.org/abs/2103.06879
代码/code:https://github.com/cv-rits/CoMoGAN
✔️ DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
论文/paper:https://arxiv.org/abs/2103.12723
代码/code:https://github.com/KumapowerLIU/DeFLOCNet
✔️ DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network
解读:https://zhuanlan.zhihu.com/p/366231002
论文/paper:https://arxiv.org/abs/2103.07893
代码/code:https://github.com/ruiliu-ai/DivCo
✔️ Diverse Semantic Image Synthesis via Probability Distribution Modeling
论文/paper:https://arxiv.org/abs/2103.06878
代码/code:https://github.com/tzt101/INADE
✔️ Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
论文/paper:https://arxiv.org/abs/2104.05376
代码/code: https://github.com/PaddlePaddle/PaddleGAN/
✔️ Efficient Conditional GAN Transfer with Knowledge Propagation across Classes
论文/paper:https://arxiv.org/abs/2102.06696
代码/code:https://github.com/mshahbazi72/cGANTransfer
✔️ Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
论文/paper:https://arxiv.org/abs/2008.00951 | 主页 | Homepage
代码/code:https://github.com/eladrich/pixel2style2pixel
Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
论文/paper:https://yunjey.github.io/
代码/code:None
✔️Generative Hierarchical Features from Synthesizing Image (CVPR 2021 (Oral))
论文/paper:https://arxiv.org/abs/2007.10379 | 主页 | Homepage
代码/code:https://github.com/genforce/ghfeat
✔️Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
论文/paper:https://arxiv.org/abs/2011.14107 | 主页 | Homepage
代码/code:https://github.com/a514514772/hijackgan
✔️HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms
论文/paper:https://arxiv.org/abs/2011.11731
代码/code:https://github.com/mahmoudnafifi/HistoGAN
✔️High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
论文/paper: https://arxiv.org/abs/2105.09188
代码/code:https://github.com/csjliang/LPTN
✔️HumanGAN: A Generative Model of Humans Images
论文/paper:https://arxiv.org/abs/2103.06902
代码/code:None
✔️ID-Unet: Iterative Soft and Hard Deformation for View Synthesis
论文/paper:https://arxiv.org/abs/2103.02264
代码/code: https://github.com/MingyuY/Iterative-view-synthesis
✔️Image-to-image Translation via Hierarchical Style Disentanglement
论文/paper:https://arxiv.org/abs/2103.01456
代码/code:https://github.com/imlixinyang/HiSD
✔️LOHO: Latent Optimization of Hairstyles via Orthogonalization
论文/paper:https://arxiv.org/abs/2103.03891
代码/code:https://github.com/dukebw/LOHO
PD-GAN: Probabilistic Diverse GAN for Image Inpainting
论文/paper:None
代码/code:https://github.com/KumapowerLIU/PD-GAN
✔️ PISE: Person Image Synthesis and Editing with Decoupled GAN
论文/paper: https://arxiv.org/abs/2103.04023
代码/code: https://github.com/Zhangjinso/PISE
✔️pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis (CVPR 2021 (Oral))
论文/paper:https://arxiv.org/abs/2012.00926 | 主页 | Homepage
代码/code:None
✔️Regularizing Generative Adversarial Networks under Limited Data
论文/paper:https://arxiv.org/abs/2104.03310 | 主页 | Homepage
代码/code:https://github.com/google/lecam-gan
✔️Teachers Do More Than Teach: Compressing Image-to-Image Models
论文/paper:https://arxiv.org/abs/2103.03467
代码/code:https://github.com/snap-research/CAT
✔️TediGAN: Text-Guided Diverse Image Generation and Manipulation
论文/paper:https://arxiv.org/abs/2012.03308
代码/code:https://github.com/weihaox/TediGAN
✔️ Training Generative Adversarial Networks in One Stage
论文/paper:https://arxiv.org/abs/2103.00430
代码/code:None
✔️Towards Real-World Blind Face Restoration with Generative Facial Prior
论文/paper: https://arxiv.org/abs/2101.04061
代码/code:None
✔️Lipstick ain't enough: Beyond Color-Matching for In-the-Wild Makeup Transfer
论文/paper:https://arxiv.org/abs/2104.01867
代码/code:https://github.com/VinAIResearch/CPM
✔️Spatially-invariant Style-codes Controlled Makeup Transfer
论文/paper:http://www.shengfenghe.com/?attachment_id=26109&download=1
代码/code:https://github.com/makeuptransfer/SCGAN
✔️DG-Font: Deformable Generative Networks for Unsupervised Font Generation
论文/paper:https://arxiv.org/abs/2104.03064
代码/code:https://github.com/ecnuycxie/DG-Font
Scene Text Telescope: Text-Focused Scene Image Super-Resolution
代码/code:None
Rethinking Text Segmentation: A Novel Dataset and a Text-Specific Refinement Approach
论文/paper:http://arxiv.org/abs/2011.14021
代码/code:None
Variational Transformer Networks for Layout Generation
论文/paper:http://arxiv.org/abs/2104.02416
代码/code:None
✔️Fourier Contour Embedding for Arbitrary-Shaped Text Detection
论文/paper:https://arxiv.org/abs/2104.10442
代码/code:https://github.com/open-mmlab/mmocr (https://www.pazhoulab.com/2021/04/1704/ 官方介绍将于 mmocr 开源)
✔️MOST: A Multi-Oriented Scene Text Detector with Localization Refinement
解读:https://zhuanlan.zhihu.com/p/362679808
论文/paper:https://arxiv.org/abs/2104.01070
代码/code:None
Progressive Contour Regression for Arbitrary-Shape Scene Text Detection
代码/code:None
Semantic-Aware Video Text Detection
代码/code:None
✔️What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
论文/paper:https://arxiv.org/abs/2103.04400
代码/code:https://github.com/ku21fan/STR-Fewer-Labels
Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter
论文/paper:http://arxiv.org/abs/2106.05920
代码/code:https://github.com/WangTianwei/Implicit-feature-alignment
A Multiplexed Network for End-to-End, Multilingual OCR
论文/paper:http://arxiv.org/abs/2103.15992
代码/code:None
✔️MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition
论文/paper:https://arxiv.org/abs/2104.01876 | 主页 / Homepage
代码/code:None
Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
论文/paper:https://arxiv.org/abs/2103.13716
代码/code:https://github.com/AyanKumarBhunia/Self-Supervised-Learning-for-Sketch
SelfDoc: Self-Supervised Document Representation Learning
论文/paper:http://arxiv.org/abs/2106.03331
代码/code:None
TAP: Text-Aware Pre-Training for Text-VQA and Text-Caption
论文/paper:http://arxiv.org/abs/2012.04638
代码/code:None
Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship
代码/code:None
Deep Texture Recognition via Exploiting Cross-Layer Statistical Self-Similarity
论文/paper:None | 介绍:https://www.pazhoulab.com/2021/04/1704/
代码/code:None
✔️Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
论文/paper:https://arxiv.org/abs/2103.06495
代码/code:https://github.com/FangShancheng/ABINet
✔️ Scene Text Retrieval via Joint Text Detection and Similarity Learning
论文/paper:https://arxiv.org/abs/2104.01552
代码/code:https://github.com/lanfeng4659/STR-TDSL
Self-attention based Text Knowledge Mining for Text Detection
论文/paper:None
代码/code:https://github.com/CVI-SZU/STKM
✔️TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text
论文/paper:https://arxiv.org/abs/2105.05486 | 主页 / Homepage
代码/code:None
✔️Towards Accurate Text-based Image Captioning with Content Diversity Exploration
论文/paper:https://github.com/guanghuixu/AnchorCaptioner/blob/main/projects/TextCap_CVPR.pdf
代码/code:https://github.com/guanghuixu/AnchorCaptioner
✔️StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval
论文/paper:https://arxiv.org/abs/2103.15706
代码/code:None
✔️QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval
论文/paper:https://arxiv.org/abs/2103.02927
代码/code:None
✔️On Semantic Similarity in Video Retrieval
论文/paper:https://arxiv.org/abs/2103.10095 | 主页 / Homepage
代码/code:https://github.com/mwray/Semantic-Video-Retrieval
✔️ Motion Representations for Articulated Animation
视频/demo:youtube
论文/paper: https://arxiv.org/abs/2104.11280 | 主页 | Homepage
代码/code:https://github.com/snap-research/articulated-animation
✔️Deep Video Matting via Spatio-Temporal Alignment and Aggregation
论文/paper:https://arxiv.org/abs/2104.11208
代码/code:https://github.com/nowsyn/DVM
✔️Improved Image Matting via Real-time User Clicks and Uncertainty Estimation
论文/paper:https://arxiv.org/abs/2012.08323
代码/code:None
Mask Guided Matting via Progressive Refinement Network
论文/paper:https://arxiv.org/abs/2012.06722
代码/code:https://github.com/yucornetto/MGMatting
✔️Omnimatte: Associating Objects and Their Effects in Video(Omnimatte
论文/paper:https://arxiv.org/abs/2105.06993 | 主页/Homepage
代码/code:None
✔️Real-Time High Resolution Background Matting
视频/demo:youtube
论文/paper:https://arxiv.org/abs/2012.07810 | 主页/Homepage
代码/code:https://github.com/PeterL1n/BackgroundMattingV2
✔️Semantic Image Matting
论文/paper:https://arxiv.org/abs/2104.08201
代码/code:https://github.com/nowsyn/SIM
✔️AdderSR: Towards Energy Efficient Image Super-Resolution
论文/paper:https://arxiv.org/abs/2009.08891
代码/code:None
✔️BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
论文/paper:https://arxiv.org/abs/2012.02181| 主页 / Homepage
代码/code:https://github.com/ckkelvinchan/BasicVSR-IconVSR
✔️ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic
论文/paper:https://arxiv.org/abs/2103.04039
代码/code:https://github.com/Xiangtaokong/ClassSR
✔️Cross-MPI: Cross-scale Stereo for Image Super-Resolution using Multiplane Images
解读:CVPR 2021,Cross-MPI以底层场景结构为线索的端到端网络,在大分辨率(x8)差距下也可完成高保真的超分辨率
论文/paper:https://arxiv.org/abs/2011.14631 | 主页 / Homepage
代码/code:None
✔️ Data-Free Knowledge Distillation For Image Super-Resolution
代码/code:None
✔️Exploring Sparsity in Image Super-Resolution for Efficient Inference
论文/paper:https://arxiv.org/abs/2006.09603
代码/code:https://github.com/LongguangWang/SMSR
✔️Flow-based Kernel Prior with Application to Blind Super-Resolution
论文/paper:https://arxiv.org/pdf/2103.15977.pdf
代码/code:https://github.com/JingyunLiang/FKP
✔️GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution
论文/paper:https://ckkelvinchan.github.io/papers/glean.pdf | 主页 / Homepage
代码/code:None
✔️Interpreting Super-Resolution Networks with Local Attribution Maps
解读:https://arxiv.org/pdf/2011.11036.pdf | CVPR2021-顾津锦:使用局部归因图理解和可视化超分辨网络
论文/paper:https://x-lowlevel-vision.github.io/lam.html
代码/code:None | colab
LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution
论文/paper:None | 主页/Homepage
代码/code:https://github.com/wangh-allen/LAU-Net
✔️Learning Continuous Image Representation with Local Implicit Image Function
论文/paper:https://arxiv.org/abs/2012.09161 | 主页/Homepage
代码/code:https://github.com/yinboc/liif
✔️MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution
论文/paper:https://jiaya.me/papers/masasr_cvpr21.pdf
代码/code:https://github.com/Jia-Research-Lab/MASA-SR
✔️Robust Reference-based Super-Resolution via C²-Matching
论文/paper:https://arxiv.org/abs/2106.01863 | 主页 / Homepage
代码/code:https://github.com/yumingj/C2-Matching
Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
论文/paper:None | 主页 / Homepage
代码/code:https://github.com/CS-GangXu/CS-GangXu
✔️ Unsupervised Degradation Representation Learning for Blind Super-Resolution
论文/paper:https://arxiv.org/abs/2104.00416
代码/code:https://github.com/LongguangWang/DASR
✔️Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscaling
论文/paper:https://arxiv.org/abs/2103.14858 | 主页 / Homepage
代码/code:https://github.com/ding3820/MIMO-VRN
✔️Multi-Stage Progressive Image Restoration
论文/paper:https://arxiv.org/abs/2102.02808
代码/code:https://github.com/swz30/MPRNet
✔️Image Inpainting with External-internal Learning and Monochromic Bottleneck
解读:https://zhuanlan.zhihu.com/p/369717594
论文/paper:https://arxiv.org/abs/2104.09068
代码/code:https://github.com/Tengfei-Wang/external-internal-inpainting
PD-GAN: Probabilistic Diverse GAN for Image Inpainting
论文/paper: http://raywzy.com/ None
代码/code:https://github.com/KumapowerLIU/PD-GAN
✔️TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations
论文/paper: https://arxiv.org/abs/2103.15982 | 主页 / Homepage
代码/code:None
✔️Anycost GANs for Interactive Image Synthesis and Editing
论文/paper:https://arxiv.org/abs/2103.03243
代码/code:https://github.com/mit-han-lab/anycost-gan
✔️DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
论文/paper:https://arxiv.org/abs/2103.12723
代码/code:https://github.com/KumapowerLIU/DeFLOCNet
✔️Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
视频/demo:youtube
论文/paper:None | 主页 / Homepage
代码/code:None
✔️High-Fidelity and Arbitrary Face Editing
论文/paper:https://arxiv.org/abs/2103.15814
代码/code:None
✔️PISE: Person Image Synthesis and Editing with Decoupled GAN
论文/paper:https://arxiv.org/abs/2103.04023
代码/code:https://github.com/Zhangjinso/PISE
✔️StyleMapGAN: Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
视频/demo:youtube
论文/paper:https://arxiv.org/abs/2104.14754
代码/code:https://github.com/naver-ai/StyleMapGAN
✔️LoFTR: Detector-Free Local Feature Matching with Transformers
论文/paper: https://arxiv.org/abs/2104.00680 | 主页 / Homepage
代码/code:https://github.com/zju3dv/LoFTR
✔️Convolutional Hough Matching Networks (CVPR 2021 Oral)
论文/paper:https://arxiv.org/abs/2103.16831 | 主页 / Homepage
代码/code:None
✔️Bridging the Visual Gap: Wide-Range Image Blending
论文/paper:https://arxiv.org/abs/2103.15149
代码/code:https://github.com/julia0607/Wide-Range-Image-Blending
✔️Contrastive Learning for Compact Single Image Dehazing
解读:对比学习去雾
论文/paper:https://arxiv.org/abs/2104.09367
代码/code: https://github.com/GlassyWu/AECR-Net
✔️Panoramic Image Reflection Removal
论文/paper:http://ci.idm.pku.edu.cn/CVPR21c.pdf
代码/code:None
✔️ Robust Reflection Removal with Reflection-free Flash-only Cues
解读:CVPR 2021 | 港科大:如何利用闪光图像(flash image)来去除反光?
论文/paper:https://arxiv.org/pdf/2103.04273
代码/code:https://github.com/ChenyangLEI/flash-reflection-removal
✔️Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection
视频/demo:youtube
论文/paper:https://arxiv.org/abs/2010.12035
代码/code:https://github.com/lucastabelini/LaneATT
✔️Focus on Local: Detecting Lane Marker from Bottom Up via Key Point
论文/paper:https://arxiv.org/abs/2105.13680
代码/code:None
✔️Global Transport for Fluid Reconstruction with Learned Self-Supervision
视频/demo:youtube
论文/paper:https://arxiv.org/abs/2104.06031 | 主页 | Homepage
代码/code:https://github.com/tum-pbs/Global-Flow-Transport
✔️CDFI: Compression-Driven Network Design for Frame Interpolation
视频demo:youtube
论文/paper:https://arxiv.org/abs/2103.10559
代码/code: https://github.com/tding1/CDFI
✔️Deep Animation Video Interpolation in the Wild
论文/paper:https://arxiv.org/abs/2104.02495
代码/code:https://github.com/lisiyao21/AnimeInterp/
✔️FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation
视频demo:youtube
论文/paper:https://arxiv.org/abs/2012.08512 | 主页 | Homepage
代码/code:https://github.com/tarun005/FLAVR
✔️3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding
论文/paper: https://arxiv.org/abs/2103.16397
代码/code:https://github.com/Gorilla-Lab-SCUT/AffordanceNet
✔️A Second-Order Approach to Learning with Instance-Dependent Label Noise (CVPR 2021 Oral)
论文/paper: https://arxiv.org/abs/2012.11854
代码/code:https://github.com/UCSC-REAL/CAL
✔️Enhancing the Transferability of Adversarial Attacks through Variance Tuning
论文/paper: https://arxiv.org/abs/2103.15571
代码/code:https://github.com/JHL-HUST/VT
✔️LiBRe: A Practical Bayesian Approach to Adversarial Detection
论文/paper: https://arxiv.org/abs/2103.14835
代码/code:None
✔️Natural Adversarial Examples
论文/paper: https://arxiv.org/abs/1907.07174
代码/code:https://github.com/hendrycks/natural-adv-examples
✔️Domain Consensus Clustering for Universal Domain Adaptation
论文/paper: http://reler.net/papers/guangrui_cvpr2021.pdf
代码/code:https://github.com/Solacex/Domain-Consensus-Clustering
✔️Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation
论文/paper: | 主页 | Homepage
代码/code:https://github.com/Hangz-nju-cuhk/Talking-Face_PC-AVS
✔️Layout-Guided Novel View Synthesis from a Single Indoor Panorama
解读:https://www.zhihu.com/question/446299297/answer/1769080299
论文/paper:https://arxiv.org/abs/2103.17022
代码/code:https://github.com/bluestyle97/PNVS
视频demo:
解读:
论文/paper:
代码/code:
参考:
https://github.com/extreme-assistant/CVPR2021-Paper-Code-Interpretation/blob/master/CVPR2021.md
https://github.com/Kobaayyy/Awesome-CVPR2021-CVPR2020-Low-Level-Vision/blob/master/CVPR2021.md
https://github.com/Qingcsai/awesome-Deepfakes
https://github.com/592McAvoy/fake-face-detection
https://githubmemory.com/repo/lkeab/CVPR-2021-Papers
https://github.com/52CV/CVPR-2021-Papers
https://github.com/amusi/CVPR2021-Papers-with-Code
https://github.com/xialeiliu/Awesome-Incremental-Learning
https://www.codetd.com/en/article/12856576
https://cv.snu.ac.kr/index.php/publication-international/
https://github.com/bismex/Awesome-person-re-identification#3-CVPR2021
https://github.com/yflv-yanxia/scene_text
https://githubmemory.com/repo/FLHonker/Awesome-Knowledge-Distillation