☪️论文下载:
密码:aicv
CVPR 2021整理:https://github.com/DWCTOD/CVPR2021-Papers-with-Code-Demo
论文下载:https://pan.baidu.com/share/init?surl=gjfUQlPf73MCk4vM8VbzoA
密码:aicv
🌟 ICCV 2021持续更新最新论文/paper和相应的开源代码/code!
🚗 ICCV 2021 收录列表:https://docs.google.com/spreadsheets/u/1/d/e/2PACX-1vRfaTmsNweuaA0Gjyu58H_Cx56pGwFhcTYII0u1pg0U7MbhlgY0R6Y-BbK3xFhAiwGZ26u3TAtN5MnS/pubhtml
🚗 官网链接:http://iccv2021.thecvf.com/home
⏲️ 时间 ⌚ 论文/paper接收公布时间:2021年7月23日
✋ 注:欢迎各位大佬提交issue,分享ICCV 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
ICCV 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:ICCV+姓名+学校/公司名称!一定要根据格式申请,可以拉你进群。
- Backbone
- Dataset
- Loss
- Vision Transformer
- 目标检测/Object Detection
- 3D目标检测 / 3D Object Detection
- 目标跟踪 / Object Tracking
- Image Semantic Segmentation
- 3D Semantic Segmentation
- 实例分割/Instance Segmentation
- 视频分割 / video semantic segmentation
- 医学图像分割/ Medical Image Segmentation
- GAN
- 细粒度分类/Fine-Grained Visual Categorization
- Geometric deep learning
- Zero/Few Shot
- Human Actions
- 手语识别/Sign Language Recognition
- Pose Estimation
- 6D Object Pose Estimation
- Face Reconstruction
- 行人重识别/Re-Identification
- 人群计数 / Crowd Counting
- Motion Forecasting
- Face-Anti-spoofing
- deepfake
- 对抗攻击/ Adversarial Attacks
- 跨模态检索/Cross-Modal Retrieval
- 深度估计 / Depth Estimation
- 视频插帧/Video Frame Interpolation
- NeRF
- 超分辨/Super-Resolution
- Image Reconstruction
- Image Desnowing
- Image Enhancement
- Matching
- 人机交互/Hand-object Interaction
- 视线估计 / Gaze Estimation
- Contrastive-Learning
- Graph Convolution Networks
- 模型压缩/Compress
- 点云/point cloud
- 字体生成/Font Generation
- Text Detection
- Scene Text Recognizer
- Autonomous-Driving
- Visdrone_detection
- 其他/Others
✔️Conformer: Local Features Coupling Global Representations for Visual Recognition
Reg-IBP: Efficient and Scalable Neural Network Robustness Training via Interval Bound Propagation
- 论文/paper:None
- 代码/code:https://github.com/harrywuhust2022/Reg_IBP_ICCV2021
Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?
- 论文/paper:https://arxiv.org/abs/2105.02498
- 代码/code:https://github.com/KingJamesSong/DifferentiableSVD
✔️FineAction: A Fined Video Dataset for Temporal Action Localization
-
论文/paper:https://arxiv.org/abs/2105.11107 | 主页/Homepage
-
代码/code: None
✔️MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
- 论文/paper:https://arxiv.org/abs/2105.07404 | 主页/Homepage
- 代码/code:https://github.com/MCG-NJU/MultiSports/
Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
-
论文/paper:None
-
代码/code: https://github.com/Anonymous-iccv2021-paper3163/CaFM-Pytorch
Bias Loss for Mobile Neural Networks
- 论文/paper:https://arxiv.org/abs/2107.11170
- 代码/code:None
Focal Frequency Loss for Image Reconstruction and Synthesis
- 论文/paper:https://arxiv.org/abs/2012.12821
- 代码/code:https://github.com/EndlessSora/focal-frequency-loss
Orthogonal Projection Loss
- 论文/paper:https://arxiv.org/abs/2103.14021
- 代码/code:https://github.com/kahnchana/opl
Rank & Sort Loss for Object Detection and Instance Segmentation (Oral)
AutoFormer: Searching Transformers for Visual Recognition
- 论文/paper:https://arxiv.org/abs/2107.00651
- 代码/code:https://github.com/microsoft/AutoML
HiFT: Hierarchical Feature Transformer for Aerial Tracking
- 论文/paper:https://arxiv.org/abs/2108.00202
- 代码/code:https://github.com/vision4robotics/HiFT
High-Fidelity Pluralistic Image Completion with Transformers
- 论文/paper:https://arxiv.org/pdf/2103.14031.pdf | 主页/Homepage
- 代码/code: https://github.com/raywzy/ICT
Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers (Oral)
- 论文/paper:https://arxiv.org/pdf/2103.15679.pdf
- 代码/code:https://github.com/hila-chefer/Transformer-MM-Explainability
PlaneTR: Structure-Guided Transformers for 3D Plane Recovery
- 论文/paper:https://arxiv.org/abs/2107.13108
- 代码/code: https://github.com/IceTTTb/PlaneTR3D
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
-
论文/paper:https://arxiv.org/abs/2102.12122
-
代码/code:https://github.com/whai362/PVT
Rethinking and Improving Relative Position Encoding for Vision Transformer
- 论文/paper:https://houwenpeng.com/publications/iRPE.pdf
- 代码/code:https://github.com/wkcn/iRPE-model-zoo
Rethinking Spatial Dimensions of Vision Transformers
- 论文/paper:https://arxiv.org/abs/2103.16302
- 代码/code:https://github.com/naver-ai/pit
Spatial-Temporal Transformer for Dynamic Scene Graph Generation
- 解读:用于视频场景图生成的Spatial-Temporal Transformer
- 论文/paper:https://arxiv.org/abs/2107.12309
- 代码/code:None
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
✔️Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
-
论文/paper:https://arxiv.org/abs/2101.11986
✔️Visual Transformer with Statistical Test for COVID-19 Classification
- 论文/paper:https://arxiv.org/abs/2107.05334
- 代码/code: None
Visual Saliency Transformer
- 论文/paper:https://arxiv.org/abs/2104.12099
- 代码/code: https://github.com/nnizhang/VST
Active Learning for Deep Object Detection via Probabilistic Modeling
- 论文/paper:https://arxiv.org/abs/2103.16130
- 代码/code:None
Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters
Conditional Variational Capsule Network for Open Set Recognition
DetCo: Unsupervised Contrastive Learning for Object Detection
-
论文/paper:https://arxiv.org/abs/2102.04803
-
代码/code: https://github.com/xieenze/DetCo
Detecting Invisible People
- 论文/paper:https://arxiv.org/abs/2012.08419 | 主页/Homepage
- 代码/code:None
FMODetect: Robust Detection and Trajectory Estimation of Fast Moving Objects
- 论文/paper:None
- 代码/code:https://github.com/rozumden/FMODetect
GraphFPN: Graph Feature Pyramid Network for Object Detection
- 论文/paper:https://arxiv.org/abs/2108.00580
- 代码/code:None
MDETR : Modulated Detection for End-to-End Multi-Modal Understanding
- 论文/paper:https://arxiv.org/abs/2104.12763 | 主页/Homepage
- 代码/code: https://github.com/ashkamath/mdetr
Rank & Sort Loss for Object Detection and Instance Segmentation (Oral)
Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency
- 论文/paper:https://arxiv.org/pdf/2107.11355.pdf
- 代码/code:None
Learn to Match: Automatic Matching Network Design for Visual Tracking
- 论文/paper:https://arxiv.org/abs/2108.00803
- 代码/code:https://github.com/JudasDie/SOTS
Calibrated Adversarial Refinement for Stochastic Semantic Segmentation
- 论文/paper:https://arxiv.org/abs/2006.13144
- 代码/code:https://github.com/EliasKassapis/CARSSS
Exploring Cross-Image Pixel Contrast for Semantic Segmentation (Oral)
- 论文/paper:https://arxiv.org/abs/2101.11939
- 代码/code:https://github.com/tfzhou/ContrastiveSeg
Enhanced Boundary Learning for Glass-like Object Segmentation
- 论文/paper:https://arxiv.org/abs/2103.15734
- 代码/code:https://github.com/hehao13/EBLNet
Labels4Free: Unsupervised Segmentation using StyleGAN
- 论文/paper:https://arxiv.org/abs/2103.14968 | 主页/Homepage
- 代码/code:None
Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation
- 论文/paper:https://arxiv.org/abs/2107.11787
- 代码/code:https://github.com/xulianuwa/AuxSegNet
Mining Latent Classes for Few-shot Segmentation(Oral)
- 论文/paper:https://arxiv.org/abs/2103.15402
- 代码/code:https://github.com/LiheYoung/MiningFSS
Personalized Image Semantic Segmentation
- 论文/paper:None
- 代码/code: https://github.com/zhangyuygss/PIS
Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation(Oral)
- 论文/paper:https://arxiv.org/abs/2107.11279
- 代码/code:https://github.com/CVMI-Lab/DARS
Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation
- 论文/paper:https://arxiv.org/abs/2107.11264v1
- 代码/code:None
VMNet: Voxel-Mesh Network for Geodesic-aware 3D Semantic Segmentation
- 论文/paper:None
- 代码/code:https://github.com/hzykent/VMNet
CDNet: Centripetal Direction Network for Nuclear Instance Segmentation
-
论文/paper:None
-
代码/code: https://github.com/2021-ICCV/CDNet
✔️Crossover Learning for Fast Online Video Instance Segmentation
-
论文/paper:https://arxiv.org/abs/2104.05970
-
代码/code: https://github.com/hustvl/CrossVIS
✔️Instances as Queries
- 论文/paper:https://arxiv.org/abs/2105.01928
- 代码/code: https://github.com/hustvl/QueryInst
Rank & Sort Loss for Object Detection and Instance Segmentation (Oral)
- 论文/paper:https://arxiv.org/abs/2107.11004
- 代码/code:https://github.com/Dayan-Guan/DA-VSN
Recurrent Mask Refinement for Few-Shot Medical Image Segmentation
- 论文/paper:https://arxiv.org/abs/2108.00622
- 代码/code:None
Manifold Matching via Deep Metric Learning for Generative Modeling
- 论文/paper:https://arxiv.org/abs/2106.10777
- 代码/code:https://github.com/dzld00/pytorch-manifold-matching
Toward Spatially Unbiased Generative Models
- 论文/paper:https://arxiv.org/abs/2108.01285
- 代码/code:None
Benchmark Platform for Ultra-Fine-Grained Visual Categorization BeyondHuman Performance
- 论文/paper:None
- 代码/code:https://github.com/XiaohanYu-GU/Ultra-FGVC
Manifold Matching via Deep Metric Learning for Generative Modeling
- 论文/paper:https://arxiv.org/abs/2106.10777
- 代码/code:https://github.com/dzld00/pytorch-manifold-matching
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
- 论文/paper:None
- 代码/code:https://github.com/csyxwei/OroJaR
Domain Generalization via Gradient Surgery
- 论文/paper:https://arxiv.org/abs/2108.01621
- 代码/code:None
Generalized Source-free Domain Adaptation
- 论文/paper:https://arxiv.org/abs/2108.01614
- 代码/code:https://github.com/Albert0147/G-SFDA
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition
-
论文/paper:https://arxiv.org/abs/2107.12213
✔️FineAction: A Fined Video Dataset for Temporal Action Localization
-
论文/paper:https://arxiv.org/abs/2105.11107 | 主页/Homepage
-
代码/code: None
✔️MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
-
论文/paper:https://arxiv.org/abs/2105.07404 | 主页/Homepage
Visual Alignment Constraint for Continuous Sign Language Recognition
- 论文/paper:https://arxiv.org/abs/2104.02330
- 代码/code: https://github.com/Blueprintf/VAC_CSLR
Hand-Object Contact Consistency Reasoning for Human Grasps Generation
- 论文/paper:https://arxiv.org/pdf/2104.03304.pdf | 主页/Homepage
- 代码/code: None
PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
- 论文/paper:https://arxiv.org/abs/2103.16507 | 主页/Homepage
- 代码/code: https://github.com/HongwenZhang/PyMAF
RePOSE: Real-Time Iterative Rendering and Refinement for 6D Object Pose Estimation
- 论文/paper:https://arxiv.org/abs/2104.00633
- 代码/code:https://github.com/sh8/RePOSE
Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing
-
论文/paper:https://arxiv.org/abs/2103.15432
-
代码/code:None
Learning Instance-level Spatial-Temporal Patterns for Person Re-identification
-
论文/paper:https://arxiv.org/abs/2108.00171
-
代码/code:https://github.com/RenMin1991/cleaned-DukeMTMC-reID/
Learning Compatible Embeddings
-
论文/paper:None
TransReID: Transformer-based Object Re-Identification
Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework (Oral)
- 论文/paper:https://arxiv.org/abs/2107.12746
- 代码/code:https://github.com/TencentYoutuResearch/CrowdCounting-P2PNet
Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting
-
论文/paper:https://arxiv.org/abs/2107.12619
-
代码/code:https://github.com/TencentYoutuResearch/CrowdCounting-UEPNet
RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting
- 论文/paper:https://arxiv.org/abs/2108.01316 | 主页/Homepage
- 代码/code:None
CL-Face-Anti-spoofing
-
论文/paper:None
- 论文/paper:https://arxiv.org/abs/2107.14480 | Dataset
- 代码/code:None
TkML-AP: Adversarial Attacks to Top-k Multi-Label Learning
- 论文/paper:https://arxiv.org/abs/2108.00146
- 代码/code:None
Wasserstein Coupled Graph Learning for Cross-Modal Retrieval
- 论文/paper:None
- 代码/code:None
AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network
- 论文/paper:None
- 代码/code:https://github.com/QT-Zhu/AA-RMVSNet
Motion Basis Learning for Unsupervised Deep Homography Estimationwith Subspace Projection
- 论文/paper:None
- 代码/code:https://github.com/NianjinYe/Motion-Basis-Homography
✔️XVFI: eXtreme Video Frame Interpolation(Oral)
-
论文/paper:https://arxiv.org/abs/2103.16206
-
代码/code: https://github.com/JihyongOh/XVFI
GNeRF: GAN-based Neural Radiance Field without Posed Camera
- 论文/paper:https://arxiv.org/abs/2103.15606 | 主页/Homepage
- 代码/code:https://github.com/MQ66/gnerf
In-Place Scene Labelling and Understanding with Implicit Scene Representation (Oral)
- 论文/paper:https://arxiv.org/abs/2103.15875 | 主页/Homepage
- 代码/code:None
KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs
Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis
- 论文/paper:https://arxiv.org/abs/2104.00677 | 主页/Homepage
- 代码/code:None
UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction (Oral)
-
论文/paper:https://arxiv.org/abs/2104.10078 | 主页/Homepage
-
代码/code:None
Learning for Scale-Arbitrary Super-Resolution from Scale-Specific Networks
-
论文/paper:https://arxiv.org/abs/2004.03791
Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
-
论文/paper:None
-
代码/code: https://github.com/Anonymous-iccv2021-paper3163/CaFM-Pytorch
Equivariant Imaging: Learning Beyond the Range Space (Oral)
-
论文/paper:https://arxiv.org/abs/2103.14756
ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss
- 论文/paper:None
- 代码/code:https://github.com/weitingchen83/ICCV2021-Single-Image-Desnowing-HDCWNet
Gap-closing Matters: Perceptual Quality Assessment and Optimization of Low-Light Image Enhancement
- 论文/paper:None
- 代码/code:https://github.com/Baoliang93/Gap-closing-Matters
Multi-scale Matching Networks for Semantic Correspondence
- 论文/paper:https://arxiv.org/abs/2108.00211
- 代码/code:None
✔️CPF: Learning a Contact Potential Field to Model the Hand-object Interaction
-
论文/paper:https://arxiv.org/abs/2012.00924
-
代码/code:https://github.com/lixiny/CPF
Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation
-
论文/paper:https://arxiv.org/abs/2107.13780 | 主页/Homepage
Social NCE: Contrastive Learning of Socially-aware Motion Representations
Parametric Contrastive Learning
-
论文/paper:https://arxiv.org/abs/2107.12028
-
代码/code:https://github.com/jiequancui/Parametric-Contrastive-Learning
MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
- 论文/paper:None
- 代码/code:https://github.com/Droliven/MSRGCN
Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks
-
论文/paper:None
-
代码/code:https://github.com/yikaiw/SNN
InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring
MVP Benchmark: Multi-View Partial Point Clouds for Completion and Registration
- 论文/paper:None |主页/Homepage
- 代码/code:https://github.com/paul007pl/MVP_Benchmark
Out-of-Core Surface Reconstruction via Global TGV Minimization
- 论文/paper:https://arxiv.org/abs/2107.14790
- 代码/code:None
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
- 论文/paper:https://arxiv.org/abs/2107.11769
- 代码/code:None
Unsupervised Point Cloud Pre-Training via View-Point Occlusion, Completion
- 论文/paper:https://arxiv.org/abs/2010.01089 |主页/Homepage
- 代码/code:https://github.com/hansen7/OcCo
Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility
- 论文/paper:None
- 代码/code:https://github.com/GDAOSU/vis2mesh
Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
✔️Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts
-
论文/paper:https://arxiv.org/abs/2104.00887
Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection
- 论文/paper:https://arxiv.org/abs/2107.12664
- 代码/code:https://github.com/GXYM/TextBPN
From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
-
论文/paper:None
Road-Challenge-Event-Detection-for-Situation-Awareness-in-Autonomous-Driving
-
论文/paper:None
ICCV2021_Visdrone_detection
-
论文/paper:None
-
代码/code:https://github.com/Gumpest/ICCV2021_Visdrone_detection
Cross-Camera Convolutional Color Constancy
-
论文/paper:https://arxiv.org/abs/2011.11164
Learnable Boundary Guided Adversarial Training
-
论文/paper:https://arxiv.org/abs/2011.11164
-
代码/code:https://github.com/FPNAS/LBGAT
Prior-Enhanced network with Meta-Prototypes (PEMP)
- 论文/paper:None
- 代码/code:https://github.com/PaperSubmitAAAA/ICCV2021-2337
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
- 论文/paper:https://arxiv.org/abs/2104.12763 | 主页/Homepage
- 代码/code:https://github.com/ashkamath/mdetr
Generalized-Shuffled-Linear-Regression (Oral)
- 论文/paper:https://drive.google.com/file/d/1Qu21VK5qhCW8WVjiRnnBjehrYVmQrDNh/view
- 代码/code:https://github.com/SILI1994/Generalized-Shuffled-Linear-Regression
VLGrammar: Grounded Grammar Induction of Vision and Language
- 论文/paper:https://arxiv.org/abs/2103.12975
- 代码/code:https://github.com/evelinehong/VLGrammar
A New Journey from SDRTV to HDRTV
- 论文/paper:None
- 代码/code:https://github.com/chxy95/HDRTVNet
IICNet: A Generic Framework for Reversible Image Conversion
- 论文/paper:None
- 代码/code:https://github.com/felixcheng97/IICNet
Structure-Preserving Deraining with Residue Channel Prior Guidance
- 论文/paper:None
- 代码/code:https://github.com/Joyies/SPDNet
Learning with Noisy Labels via Sparse Regularization
- 论文/paper:https://arxiv.org/abs/2108.00192
- 代码/code:https://github.com/hitcszx/lnl_sr
Neural Strokes: Stylized Line Drawing of 3D Shapes
- 论文/paper:None
- 代码/code:https://github.com/DifanLiu/NeuralStrokes
COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation
- 论文/paper:None
- 代码/code:https://github.com/kywen1119/COOKIE
RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth
- 论文/paper:https://arxiv.org/abs/2108.00616
- 代码/code:None
ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description
- 论文/paper:https://arxiv.org/abs/2108.00355
- 代码/code:None
Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction
- 论文/paper:https://arxiv.org/abs/2108.00238
- 代码/code:None
CanvasVAE: Learning to Generate Vector Graphic Documents
- 论文/paper:https://arxiv.org/abs/2108.01249
- 代码/code:None