CVPR-2022-Papers

官网链接：https://cvpr2022.thecvf.com/

开会时间：2022年6月19日-6月24日

❣❣❣近日，CVPR 2022 接收论文公布！ 总计2067篇！，部分预印版论文也陆续发布中，本文档也将持续收录更新，多多关注!!

❣❣❣另外打包下载所有论文，可在【我爱计算机视觉】微信公众号后台回复“paper”。截止6月13日，已收录 733+2 篇。

历年综述论文分类汇总戳这里↘️CV-Surveys施工中~~~~~~~~~~

2022 年论文分类汇总戳这里

↘️CVPR-2022-Papers ↘️WACV-2022-Papers

2021年论文分类汇总戳这里

↘️ICCV-2021-Papers ↘️CVPR-2021-Papers

2020 年论文分类汇总戳这里

↘️CVPR-2020-Papers ↘️ECCV-2020-Papers

❗❗❗ 6月13日更新 2 篇

• 目标计数
  • Rethinking Spatial Invariance of Convolutional Networks for Object Counting
    ⭐code📰解读
• 三维网格重建
  • Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes
    ⭐code📰解读

❗❗❗ 6月10日更新 6 篇

• 视频预测
  • STIP: A SpatioTemporal Information-Preserving and Perception-Augmented Model for High-Resolution Video Prediction
    ⭐code📰解读
• SR
  • VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
    🏠project📰解读
• 图像矢量化
  • Towards Layer-wise Image Vectorization
    😮oral⭐code📰解读
• 模型压缩
  • DiSparse: Disentangled Sparsification for Multitask Model Compression
    ⭐code📰解读
• 动作检测
  • GateHUB: Gated History Unit with Background Suppression for Online Action Detection
• 数据集
  • Open Challenges in Deep Stereo: the Booster Dataset
    🌻dataset

❗❗❗ 6月9日更新 2 篇

• 多标签分类
  • Large Loss Matters in Weakly Supervised Multi-Label Classification
    ⭐code🏠project
• VOS
  • Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation
    ⭐code🏠project

目录

🐱	🐶	🐯	🐺
1.其它	2.Image Segmentation(图像分割)	3.Image Progress(图像处理)	4.Image Captioning(图像字幕)
5.Object Detection(目标检测)	6.Object Tracking(目标跟踪)	7.Point Cloud(点云)	8.Action Detection(人体动作检测与识别)
9.Human Pose Estimation(人体姿态估计)	10.3D(三维视觉)	11.Face	12.Image-to-Image Translation(图像到图像翻译)
13.GAN	14.Video	15.Transformer	16.Semi/self-supervised learning(半/自监督)
17.Medical Image(医学影像)	18.Person Re-Identification(人员重识别)	19.Neural Architecture Search(神经架构搜索)	20.Autonomous vehicles(自动驾驶)
21.UAV/Remote Sensing/Satellite Image(无人机/遥感/卫星图像)	22.Image Synthesis/Generation(图像合成)	23.Image Retrieval(图像检索)	24.Super-Resolution(超分辨率)
25.Fine-Grained/Image Classification(细粒度/图像分类)	26.GCN/GNN	27.Pose Estimation(物体姿势估计)	28.Style Transfer(风格迁移)
29.Augmented Reality/Virtual Reality/Robotics(增强/虚拟现实/机器人)	30.Visual Answer Questions(视觉问答)	31.Vision-Language(视觉语言)	32.Data Augmentation(数据增强)
33.Human-Object Interaction(人物交互)	34.Model Compression/Knowledge Distillation/Pruning(模型压缩/知识蒸馏/剪枝)	35.OCR	36.Optical Flow(光流估计)
37.Contrastive Learning(对比学习)	38.Meta-Learning(元学习)	39.Continual Learning(持续学习)	40.Adversarial Learning(对抗学习)
41.Incremental Learning(增量学习)	42.Metric Learning(度量学习)	43.Multi-Task Learning(多任务学习)	44.Federated Learning(联邦学习)
45.Dense Prediction(密集预测)	46.Scene Graph Generation(场景图生成)	47.Few/Zero-Shot Learning/Domain Generalization/Adaptation(小/零样本/域泛化/适应)	48.Visual Grounding
49.Image Geo-localization(图像地理定位)	50.Anomaly Detection(异常检测)	51.光学、几何、光场成像	52.Human Motion Forecasting(人体运动预测)
53.Sign Language Translation(手语翻译)	54.Dataset(数据集)	55.Novel View Synthesis(视图合成)	56.Sound
57.Gaze Estimation(视线估计)	58.Neural rendering(神经渲染)	59.动画	60.Visual Emotion Analysis(视觉情感分析)

Machine Translation(机器翻译)

• VALHALLA: Visual Hallucination for Machine Translation
  🏠project

Object Counting(目标计数)

• Rethinking Spatial Invariance of Convolutional Networks for Object Counting
  ⭐code📰解读

computer-aided design (CAD)

• Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
  ⭐code

60.Visual Emotion Analysis(视觉情感分析)

• MDAN: Multi-level Dependent Attention Network for Visual Emotion Analysis

59.动画

图像动画

• Thin-Plate Spline Motion Model for Image Animation
• 人物动画
  • Structured Local Radiance Fields for Human Avatar Modeling
• 3D character animation(三维角色动画)
  • 皮肤预测
    • SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters
      🏠project
• 3D 舞蹈生成
  • Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory

58.Neural rendering(神经渲染)

• Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Camera
• IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images
  😮oral🏠project
• SqueezeNeRF: Further factorized FastNeRF for memory-efficient inference
• Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
  ⭐code
• Modeling Indirect Illumination for Inverse Rendering
  ⭐code🏠project
• GenDR: A Generalized Differentiable Renderer
  ⭐code
  泛化可微渲染器
• CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields
  ⭐code🏠project
• NeRF-Editing: Geometry Editing of Neural Radiance Fields

57.Gaze Estimation(视线估计)

• GazeOnce: Real-Time Multi-Person Gaze Estimation

56.Sound

• 声源定位
  • Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes
    ⭐code

55.Novel View Synthesis(视图合成)

• NPBG++: Accelerating Neural Point-Based Graphics
  🏠project
• AutoRF: Learning 3D Object Radiance Fields from Single View Observations
  🏠project
• NeurMiPs: Neural Mixture of Planar Experts for View Synthesis
  ⭐code🏠project📺video📰解读

54.Dataset(数据集)

• ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer
  ⭐code🏠project📰粗解
• Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities
• 3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos
• Hephaestus: A large scale multitask dataset towards InSAR understanding
• SmartPortraits: Depth Powered Handheld Smartphone Dataset of Human Portraits for State Estimation, Reconstruction and Synthesis
  🌻dataset
• AKB-48: A Real-World Articulated Object Knowledge Base
  ⭐code
  📰粗解
• Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitives
• 卫星数据集
  • DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation
• 动物行为理解数据集
  • Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding
    😮oral🏠project🌻dataset

53.Sign Language Translation(手语翻译)

• A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

52.Human Motion Forecasting(人体运动预测)

• Motron: Multimodal Probabilistic Human Motion Forecasting
• Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction

51.光学、几何、光场成像

• Light Field(光场)
  • Occlusion-Aware Cost Constructor for Light Field Depth Estimation
    ⭐code📰粗解
• 深度重建
  • Deep Hyperspectral-Depth Reconstruction Using Single Color-Dot Projection
    ⭐code🏠project📺video
• 快门校正
  • Learning Adaptive Warping for Real-World Rolling Shutter Correction
    ⭐code
• 热红外成像
  • Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real World
    😮oral

50.Anomaly Detection(异常检测)

• Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection
  ⭐code
• Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection
  ⭐code

49.Image Geo-localization(图像地理定位)

• TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization
  ⭐code
• 视觉地理定位
  • Rethinking Visual Geo-localization for Large-Scale Applications
    ⭐code
  • Deep Visual Geo-localization Benchmark
    😮oral🏠project
• 轨迹重建
  • MonoTrack: Shuttle trajectory reconstruction from monocular badminton video

48.Visual Grounding

• Multi-View Transformer for 3D Visual Grounding
  ⭐code
• Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning
  ⭐code
  视觉定位，通过自然语言定位目标位置 （很有意思的研究）

47.Few/Zero-Shot Learning/Domain Generalization/Adaptation(小/零样本/域泛化/适应)

• 小样本
  • Few-shot Learning with Noisy Labels
  • Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
    🏠project📺video
  • Few-shot Backdoor Defense Using Shapley Estimation
    📰解读
• 零样本
  • MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning
    ⭐code📰粗解
  • Unseen Classes at a Later Time? No Problem
    ⭐code
  • KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning
    ⭐code
    📰解读
• 域泛化
  • Compound Domain Generalization via Meta-Knowledge Encoding
  • Causality Inspired Representation Learning for Domain Generalization
  • Towards Unsupervised Domain Generalization
    本次任务的主要目标是域泛化（domain generalization(DG)），是首篇将DG推广到unsupervised learning 领域的，并提出一个新的研究领域 unsupervised domain generalization(UDG)。
  • 域外泛化
    • The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization
• 域适应
  • Continual Test-Time Domain Adaptation
    ⭐code
  • Safe Self-Refinement for Transformer-based Domain Adaptation
    ⭐code📰解读
  • Source-Free Domain Adaptation via Distribution Estimation
    📰解读
  • Learning Distinctive Margin toward Active Domain Adaptation
    ⭐code
    📰解读
  • 无监督域适应
    • Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
      ⭐code

46.Scene Graph Generation(场景图生成)

• HL-Net: Heterophily Learning Network for Scene Graph Generatio
  ⭐code
  场景图生成：异质学习网络
  📰解读
• RU-Net: Regularized Unrolling Network for Scene Graph Generation
  ⭐code
  场景图生成：正则展开网络
  📰解读
• The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation
  ⭐code

45.Dense Prediction(密集预测)

• Does Robustness on ImageNet Transfer to Downstream Tasks?

44.Federated Learning(联邦学习)

• CD2-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning
• Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage
  ⭐code
• FedCorr: Multi-Stage Federated Learning for Label Noise Correction
  ⭐code
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning

43.Multi-Task Learning(多任务学习)

• Controllable Dynamic Multi-Task Architectures
• Task Adaptive Parameter Sharing for Multi-Task Learning

42.Metric Learning(度量学习)

• Self-Taught Metric Learning without Labels

41.Incremental Learning(增量学习)

• 增量学习
  • Energy-based Latent Aligner for Incremental Learning
    ⭐code
  • General Incremental Learning with Domain-aware Categorical Representations
• 类增量学习
  • Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches
  • Constrained Few-shot Class-incremental Learning
    ⭐code
  • Class-Incremental Learning with Strong Pre-trained Models

40.Adversarial Learning(对抗学习)

• Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness
• Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network
• Towards Practical Certifiable Patch Defense with Vision Transformer
  📰解读
• 对抗样本
  • Label-Only Model Inversion Attacks via Boundary Repulsion
  • Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection
    ⭐code
• 对抗攻击
  • Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
• 黑盒
  • Investigating Top-k White-Box and Transferable Black-box Attack
    ⭐code
  • DST: Dynamic Substitute Training for Data-free Black-box Attack
  • Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees
    😮oral
• 对抗训练
  • LAS-AT: Adversarial Training with Learnable Attack Strategy
    😮oral⭐code
    📰CVPR 2022 中科院、腾讯提出LAS-AT，利用“可学习攻击策略”进行“对抗训练”

39.Continual Learning(持续学习)

• On Generalizing Beyond Domains in Cross-Domain Continual Learning
• Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
• Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries
  ⭐code

38.Meta-Learning(元学习)

• What Matters For Meta-Learning Vision Regression Tasks?
• Multidimensional Belief Quantification for Label-Efficient Meta-Learning
• Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning

37.Contrastive Learning(对比学习)

• Selective-Supervised Contrastive Learning with Noisy Labels
  ⭐code📰粗解
• Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
  ⭐code
• Cam-Ready: UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning
• Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework
  ⭐code
• Crafting Better Contrastive Views for Siamese Representation Learning
  😮oral⭐code

36.Optical Flow(光流估计)

• CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow
  ⭐code
• DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow
• Imposing Consistency for Optical Flow Estimation
• Deep Equilibrium Optical Flow Estimation
  ⭐code📰解读
• GMFlow: Learning Optical Flow via Global Matching
  😮oral⭐code📰解读

35.OCR

• 场景文本检测
  • Towards End-to-End Unified Scene Text Detection and Layout Analysis
    ⭐code
  • Pushing the Performance Limit of Scene Text Recognizer without Human Annotation
  • Vision-Language Pre-Training for Boosting Scene Text Detectors
    视觉语言预训练，场景文本检测,代码将开源，地址尚未公布。
• Text Spotting
  • Text Spotting Transformers
    ⭐code📰粗解
• LOGO设计
  • Aesthetic Text Logo Synthesis via Content-aware Layout Inferring
    ⭐code
    📰CVPR 2022 | 北大、腾讯提出文字logo生成模型，脑洞大开堪比设计师
• 字体生成
  • XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation
  • (Oral)Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator
    字体生成（很有商业价值的方向）
  • Few-Shot Font Generation by Learning Fine-Grained Local Styles
• 文本识别
  • Open-set Text Recognition via Character-Context Decoupling
• 表格结构识别
  • Neural Collaborative Graph Machines for Table Structure Recognition
    📰解读

34.Model Compression/Knowledge Distillation/Pruning(模型压缩/知识蒸馏/剪枝)

• 知识蒸馏
  • Knowledge Distillation with the Reused Teacher Classifier
  • DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers
    📰解读
  • Decoupled Knowledge Distillation
    ⭐code
    📰解耦知识蒸馏，让Hinton在7年前提出的方法重回SOTA行列
  • Knowledge Distillation via the Target-aware Transformer
    😮oral
    📰RMIT&阿里&UTS&中山提出Target-aware Transformer，进行one-to-all知识蒸馏！性能SOTA
  • Evaluation-oriented Knowledge Distillation for Deep Face Recognition
    😮oral⭐code📰解读
• 模型压缩
  • CHEX: CHannel EXploration for CNN Model Compression
• 剪枝
  • Revisiting Random Channel Pruning for Neural Network Compression
    ⭐code
    📰解读
• 量化
  • A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information
    ⭐code🏠project

33.Human-Object Interaction(人物交互)

• HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
• MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection
• GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection
  ⭐code
• OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction
  ⭐code
  📰粗解
• D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions
  🏠code
• What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions
  😮oral
• Human-Object Interaction Detection via Disentangled Transformer
• Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection
  ⭐code📰解读
• Interactiveness Field in Human-Object Interactions
  ⭐code
• Stability-driven Contact Reconstruction From Monocular Color Images
  ⭐code
  单目彩色图像的手物交互重建，人机交互
• Interactiveness Field of Human-Object Interactions
  ⭐code
  📰粗解
• HOI跟踪
  • BEHAVE: Dataset and Method for Tracking Human Object Interactions
    🏠project

32.Data Augmentation(数据增强)

• 🐦️AlignMix: Improving representation by interpolating aligned features
• 3D Common Corruptions and Data Augmentation
  ⭐code🏠project📺video📰粗解
• Kubric: A scalable dataset generator

31.Vision-Language(视觉语言)

• Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationships
• VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers
• Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality
  🌻dataset
• Robust Cross-Modal Representation Learning with Progressive Self-Distillation
• Prompt Distribution Learning
  在下游的识别任务中，作者提出的方法在12个数据集上均展示出了一致性的性能提升。
• Vision-Language Pre-Training with Triple Contrastive Learning
  ⭐code
• Improving features Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning
  ⭐code
  📰国科大&港中文提出带视觉语言验证和迭代推理的Visual Grounding框架，性能SOTA，代码已开源！
• VLN
  • EnvEdit: Environment Editing for Vision-and-Language Navigation
    ⭐code
  • Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation
  • Reinforced Structured State-Evolution for Vision-Language Navigation
    ⭐code📰解读

30.Visual Answer Questions(视觉问答)

• VQA
  • SimVQA: Exploring Simulated Environments for Visual Question Answering
    🏠project
  • SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering
    ⭐code📰粗解
• AVQA
  • Learning to Answer Questions in Dynamic Audio-Visual Scenarios
    😮oral⭐code
    📰CVPR 2022 Oral | 人大高瓴AI学院提出面向动态视音场景的问答学习任务
• Video-QA
  • Measuring Compositional Consistency for Video Question Answering
  • Invariant Grounding for Video Question Answering
    😮oral⭐code📰解读

29.Augmented Reality/Virtual Reality/Robotics(增强/虚拟现实/机器人)

• 目标导航
  • Online Learning of Reusable Abstract Models for Object Goal Navigation
• try-on
  • Dressing in the Wild by Watching Dance Videos
    🏠project
  • Style-Based Global Appearance Flow for Virtual Try-On
    ⭐code
  • ClothFormer:Taming Video Virtual Try-on in All Module
    😮oral⭐code🏠project📰解读
• AR
  • Episodic Memory Question Answering
    😮oral⭐code
    AI助理：情景记忆问答 （增强现实新任务，数据及代码均将开源）
• 机器人
  • 手-物姿态估计
    • ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis
      ⭐code
      📰粗解

28.Style Transfer(风格迁移)

• Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer
  ⭐code
• Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation
  ⭐code
• 运动风格迁移
  • Style-ERD: Responsive and Coherent Online Motion Style Transfer
• 运动迁移
  • Structure-Aware Motion Transfer with Deformable Anchor Model
    ⭐code📰解读
• 场景风格化
  • StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning

27.Pose Estimation(物体姿势估计)

• OSOP: A Multi-Stage One Shot Object Pose Estimation Framework
• OnePose: One-Shot Object Pose Estimation without CAD Models
  ⭐code🏠project📰解读
• 4D
  • Revealing Occlusions with 4D Neural Fields
    😮oral⭐code🏠project
• 9D
  • CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild
    ⭐code📰粗解📓
• 单目目标姿势估计
  • EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
    ⭐code
• 6D
  • RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization
  • FS6D: Few-Shot 6D Pose Estimation of Novel Objects
    ⭐code🏠project📰解读
  • Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation
  • ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework
    ⭐code
  • Focal Length and Object Pose Estimation via Render and Compare
    ⭐code🏠project📰解读
  • DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation
    ⭐code🏠project📰解读
  • Coupled Iterative Refinement for 6D Multi-Object Pose Estimation
    ⭐code📰解读
• 3D Object Articulation
  • Understanding 3D Object Articulation in Internet Videos
    🏠project
• 3Dope
  • Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions
    ⭐code

26.GCN/GNN

• GNN
  • 🐦️Lifelong Graph Learning
    ⭐code
  • AEGNN: Asynchronous Event-based Graph Neural Networks
  • "The Pedestrian next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping

25.Fine-Grained/Image Classification(细粒度/图像分类)

• 细粒度分类
  • Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information
    ⭐code📰粗解📓
• 图像分类
  • DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification
    ⭐code
  • Contrastive Test-Time Adaptation
    🏠project
• 小样本分类
  • CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification
  • Matching Feature Sets for Few-Shot Image Classification
    ⭐code🏠project📺video
  • Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification
    😮oral⭐code🏠project📰解读
  • Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification
    📰解读
  • Generating Representative Samples for Few-Shot Classification
    ⭐code
    📰粗解
    在小样本分类问题中，通过生成更多代表性样本，去除非代表性样本，改善了分类结果。实现了SOTA的结果。
  • 小样本分类与分割(FS-CS)
    • Integrative Few-Shot Learning for Classification and Segmentation
• 长尾识别
  • Nested Collaborative Learning for Long-Tailed Visual Recognition
  • Long-Tailed Recognition via Weight Balancing
    ⭐code
  • Targeted Supervised Contrastive Learning for Long-Tailed Recognition
• 细粒度识别
  • Knowledge Mining with Scene Text for Fine-Grained Recognition
    ⭐code📰解读
• 多标签分类
  • Large Loss Matters in Weakly Supervised Multi-Label Classification
    ⭐code🏠project

24.Super-Resolution(超分辨率)

• Learning Graph Regularisation for Guided Super-Resolution
• Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites
  ⭐code🏠project📰解读
• Deep Constrained Least Squares for Blind Image Super-Resolution
  ⭐code📰解读

23.Image Retrieval(图像检索)

• Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval
  ⭐code
• Correlation Verification for Image Retrieval
  😮oral⭐code
• Sketch3T: Test-Time Training for Zero-Shot SBIR
• Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image
• 文本-视频检索
  • X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
    🏠project
    📰X-Pool：多伦多大学提出基于文本的视频聚合方式，在视频文本检索上达到SOTA性能！
  • Bridging Video-text Retrieval with Multiple Choice Questions
    ⭐code
    📰《BridgeFormer》港大&腾讯&伯克利提出带有多项选择任务的视频文本检索模型，性能SOTA！
• 跨模太检索
  • ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval

22.Image Synthesis/Generation(图像合成)

• Interactive Image Synthesis with Panoptic Layout Generation
• Autoregressive Image Generation using Residual Quantization
  ⭐code📰粗解
• GIRAFFE HD: A High-Resolution 3D-aware Generative Model
• Arbitrary-Scale Image Synthesis
  ⭐code📰粗解
• Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis
  ⭐code📰解读
• Learning to Memorize Feature Hallucination for One-Shot Image Generation
  📰解读
• 文本引导的图像处理
  • ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation
    😮oral🏠project
• 姿势引导的图像合成
  • Exploring Dual-task Correlation for Pose Guided Person Image Generation
    ⭐code📰粗解
• 文本到图像合成
  • StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis
  • Text-to-Image Synthesis based on Object-Guided Joint-Decoding Transformer
    📰解读
  • LAFITE: Towards Language-Free Training for Text-to-Image Generation
    ⭐code
• 图像翻译
  • FlexIT: Towards Flexible Semantic Image Translation
  • A Style-aware Discriminator for Controllable Image Translation
• 图像生成
  • Marginal Contrastive Correspondence for Guided Image Generation
    😮oral
  • OSSGAN: Open-Set Semi-Supervised Image Generation
    ⭐code
  • A Closer Look at Few-shot Image Generation

21.UAV/Remote Sensing/Satellite Image(无人机/遥感/卫星图像)

• 遥感图像融合
  • HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening
    ⭐code📰粗解
• 航空图像分割
  • Revisiting Near/Remote Sensing with Geospatial Attention

20.Autonomous vehicles(自动驾驶)

• 自动驾驶
  • Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data
  • Exploiting Temporal Relations on Radar Perception for Autonomous Driving
  • COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles
    ⭐code🏠project📰解读
• 车道线检测
  • Rethinking Efficient Lane Detection via Curve Modeling
    ⭐code📰粗解
    📓
  • Towards Driving-Oriented Metric for Lane Detection Models
  • A Keypoint-based Global Association Network for Lane Detection
    ⭐code📰解读
  • 单目3D车道检测
    • ONCE-3DLanes: Building Monocular 3D Lane Detection
      ⭐code
      车道线检测技术再演进
• 车道线描述
  • Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes
    ⭐code
  • CLRNet: Cross Layer Refinement Network for Lane Detection
    📰解读
• 行为预测
  • 🐦️JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection
• 自动驾驶场景重新照明
  • SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Tasks
    🏠project

19.Neural Architecture Search(神经架构搜索)

• 🐦️ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior
• Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search
  ⭐code📰解读
• GPUNet: Searching the Deployable Convolution Neural Networks for GPUs
  神经架构搜索，面向GPUs部署的轻量级网络结构搜索 （比谷歌EfficientNet-X系列、Meta FBNetV3 速度更快，甚至性能都要好，作者来自英伟达）

18.Person Re-Identification(人员重识别)

• Reid
  • Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
    ⭐code
  • Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification
  • Large-Scale Pre-training for Person Re-identification with Noisy Labels
    ⭐code
  • Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification
    ⭐code
  • Implicit Sample Extension for Unsupervised Person Re-Identification
    ⭐code📰解读
  • Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification
    ⭐code
  • NFormer: Robust Person Re-identification with Neighbor Transformer
    ⭐code📰解读
  • Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification
  • 换装行人重识别
    • Clothes-Changing Person Re-identification with RGB Modality Only
      ⭐code📰解读
  • 遮挡行人重识别
    • Feature Erasing and Diffusion Network for Occluded Person Re-Identification
• 人群计数
  • Leveraging Self-Supervision for Cross-Domain Crowd Counting
  • Boosting Crowd Counting via Multifaceted Attention
    ⭐code
  • Bi-level Alignment for Cross-Domain Crowd Counting
    ⭐code
    📰解读
• 行人检测
  • STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes
    ⭐code
• 步态识别
  • Gait Recognition in the Wild with Dense 3D Representations and A Benchmark
    ⭐code🏠project
    📰解读
• Person Search
  • PSTR: End-to-End One-Step Person Search With Transformers
    ⭐code

17.Medical Image(医学影像)

• Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations
• BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
• DeepLIIF: An Online Platform for Quantification of Clinical Pathology Slides
• DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis
  ⭐code📰解读
• Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning
  ⭐code🏠project
• 3D生物打印
  • Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction to Treat Diabetic Foot Ulcers
    利用伤口分割和重建生成3D生物打印贴片来治疗糖尿病足溃疡
• SR（ＭRI）
  • Transformer-empowered Multi-scale Contextual Matching and Aggregation for Multi-contrast MRI Super-resolution
    ⭐code
• 医学图像配准
  • Affine Medical Image Registration with Coarse-to-Fine Vision Transformer
    ⭐code
• 医学图像分析
  • FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
    ⭐code📰解读
• 自动生成报告
  • Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation

16.Semi/self-supervised learning(半/自监督)

• 自监督
  • A study on the distribution of social biases in self-supervised learning visual models
  • Learning Where to Learn in Cross-View Self-Supervised Learning
  • Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy
• 半监督
  • Class-Aware Contrastive Semi-Supervised Learning
    📰解读
  • RSCFed: Random Sampling Consensus Federated Semi-supervised Learning
    ⭐code
  • FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering
    😮oral🏠project
  • Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels
• 弱监督
  • P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision
    ⭐code
    使用教学视频进行概率性程序规划的弱监督方法

15.Transformer

• Fast Point Transformer
• ChiTransformer:Towards Reliable Stereo from Cues
• Beyond Fixation: Dynamic Window Visual Transformer
• Training-free Transformer Architecture Search
  📰解读
• Automated Progressive Learning for Efficient Training of Vision Transformers
  ⭐code
• Collaborative Transformers for Grounded Situation Recognition
  ⭐code
• TubeDETR: Spatio-Temporal Video Grounding with Transformers
  😮oral⭐code🏠project
• Deformable Video Transformer
• MixFormer: Mixing Features across Windows and Dimensions
  😮oral⭐code📰粗解
• Are Multimodal Transformers Robust to Missing Modality?
• MiniViT: Compressing Vision Transformers with Weight Multiplexing
• Multimodal Token Fusion for Vision Transformers
• Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
  😮oral⭐code📰解读
• UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
  对比学习用于视觉对话的统一Transformer架构
• Patch Slimming for Efficient Vision Transformers
  📰解读
• Swin Transformer V2: Scaling Up Capacity and Resolution
  ⭐code
  📰大大刷新记录！Swin Transformer v2.0 来了，30亿参数！
• SimMIM: A Simple Framework for Masked Image Modeling
  ⭐code
• NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition
  ⭐code
  📰解读
• Mobile-Former: Bridging MobileNet and Transformer
• MulT: An End-to-End Multitask Learning Transformer
• Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning
  😮oral⭐code📰解读
• 形状补全
  • ShapeFormer: Transformer-based Shape Completion via Sparse Representation
    ⭐code🏠project

14.Video

• Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models
  😮oral
• 动作分割
  • Unsupervised Activity Segmentation by Joint Representation Learning and Online Clustering
    📺video
  • Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos
• 动作理解
  • How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs
  • Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos
    ⭐code
• Video Copy Detection(视频拷贝检测)
  • A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection
    ⭐code
• 视频合成
  • Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning
    ⭐code
  • 3D Moments from Near-Duplicate Photos
    🏠project
• 视频异常检测
  • Generative Cooperative Learning for Unsupervised Video Anomaly Detection
  • Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection
• 视频监控
  • 轨迹预测
    • How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting
    • Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion
      ⭐code
    • Non-Probability Sampling Network for Stochastic Human Trajectory Prediction
      ⭐code
• 视频时刻检索和视频高光检测
  • UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection
    ⭐code
  • Learning Pixel-Level Distinctions for Video Highlight Detection
• 视频时刻检索
  • AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval
• 视频预测
  • STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Prediction
  • Continual Predictive Learning from Videos
    😮oral⭐code
• 视频个体计数
  • DR.VIC: Decomposition and Reasoning for Video Individual Counting
    ⭐code
• 视频插值
  • Many-to-many Splatting for Efficient Video Frame Interpolation
    ⭐code
  • TimeReplayer: Unlocking the Potential of Event Cameras for Video Interpolation
  • Long-term Video Frame Interpolation via Feature Propagation
  • Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion
• 视觉对应（视频）
  • Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning
    ⭐code
• 视频识别
  • BEVT: BERT Pretraining of Video Transformers
    ⭐code
    📰视频Transformer自监督预训练新范式，复旦、微软云AI实现视频识别新SOTA
• 视频分类
  • 零样本视频分类
    • Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification
• 视频预测
  • 手部动作预测
    • Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos
      🏠project📺video
• 视频分割
  • Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation
    ⭐code
  • VOS
    • Recurrent Dynamic Embedding for Video Object Segmentation
      ⭐code
    • Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation
      ⭐code🏠project
  • 视频实例分割(VIS)
    • Efficient Video Instance Segmentation via Tracklet Query and Proposal
      🏠project📺video📰粗解
    • Temporally Efficient Vision Transformer for Video Instance Segmentation
      😮oral⭐code📰解读
  • 视频语义分割
    • Coarse-to-Fine Feature Mining for Video Semantic Segmentation
      ⭐code
  • 视频全景分割
    • Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation
      😮oral⭐code📰解读
• 视频影像处理
  • 视频超分辨率
    • Reference-based Video Super-Resolution Using Multi-Camera Video Triplets
    • Learning Trajectory-Aware Transformer for Video Super-Resolution
      😮oral⭐code
    • Investigating Tradeoffs in Real-World Video Super-Resolution
      ⭐code📰解读
    • BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
      ⭐code🏠project📺video
      🏆NTIRE 2021年视频修复和增强挑战赛冠军
    • Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling
      📰ETDM：基于显式时间差分建模的视频超分辨率
    • Memory-Augmented Non-Local Attention for Video Super-Resolution
      📰解读
  • 视频恢复
    • Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global Reset Feature
      ⭐code
  • 视频修复
    • Towards An End-to-End Framework for Flow-Guided Video Inpainting
  • 视频去摩尔纹
    • Video Demoireing with Relation-Based Temporal Consistency
      🏠project📺video
  • 视频去模糊
    • Multi-Scale Memory-Based Video Deblurring
  • 视频去噪
    • Dancing under the stars: video denoising in starlight
      ⭐code
  • 电影修复
    • Bringing Old Films Back to Life
      ⭐code
• 视频表征学习
  • TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition
    😮oral⭐code📰解读
  • 自监督视频表征学习
    • Hierarchical Self-supervised Representation Learning for Movie Understanding
      ⭐code🏠project
    • Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency
    • Cross-Architecture Self-supervised Video Representation Learning
      ⭐code📰解读
  • 视频对比学习
    • Probabilistic Representations for Video Contrastive Learning
• 视频分解
  • Deformable Sprites for Unsupervised Video Decomposition
    😮oral🏠project
• 视频阴影检测
  • Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
    ⭐code
• 视频帧插值
  • IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation
    📰解读
  • Video Frame Interpolation with Transformer
    ⭐code
    📰解读
• VSS
  • Scene Consistency Representation Learning for Video Scene Segmentation
    ⭐code
    📰解读
• VSR
  • Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning
    ⭐code
    📰解读
• 视频重建
  • Context-Aware Video Reconstruction for Rolling Shutter Cameras
    ⭐code📰解读
• 视频理解
  • Revisiting the "Video" in Video-Language Understanding
    😮oral⭐code

13.GAN

• 🐦️HyperInverter: Improving StyleGAN Inversion via Hypernetwork
  🏠project
• InsetGAN for Full-Body Image Generation
  🏠project
  📰1024x1024 分辨率，效果惊人！InsetGAN：全身图像生成
• Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data
  ⭐code
• Deep Image-based Illumination Harmonization
• GAN-Supervised Dense Visual Alignment
  😮oral⭐code🏠project📺video
  📰CVPR2022 Oral：GAN监督的密集视觉对齐，代码开源
• HairMapper: Removing Hair from Portraits Using GANs
  ⭐code
• Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps
  😮oral🏠project
• 图像篡改检测
  • Proactive Image Manipulation Detection
    ⭐code
• 头发编辑
  • HairCLIP: Design Your Hair by Text and Reference Image
    ⭐code

12.Image-to-Image Translation(图像到图像翻译)

• Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks
• Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation
• InstaFormer: Instance-Aware Image-to-Image Translation with Transformer
• Unsupervised Image-to-Image Translation with Generative Prior
  ⭐code🏠project📺video

11.Face(人脸)

• Protecting Celebrities with Identity Consistency Transformer
• Deepfake
  • Voice-Face Homogeneity Tells Deepfake
    ⭐code📰粗解
• 妆容迁移
  • Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer
• 人脸识别
  • Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation
  • Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC
    ⭐code
  • AdaFace: Quality Adaptive Margin for Face Recognition
    😮oral⭐code
• 人脸表情识别
  • Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin
    ⭐code
• 3D人脸
  • ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations
  • Learning to Restore 3D Face from In-the-Wild Degraded Images
    📰解读
• 活体检测
  • PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition
• 假脸检测
  • Exploring Frequency Adversarial Attacks for Face Forgery Detection
    📰粗解
• 人脸交换
  • High-resolution Face Swapping via Latent Semantics Disentanglement
    ⭐code
• 人脸属性分类
  • Fair Contrastive Learning for Facial Attribute Classification
    ⭐code
• Face Relighting(人脸重照光)
  • Face Relighting with Geometrically Consistent Shadows
• 人脸编辑
  • TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
    ⭐code🏠project
• 人脸幻构
  • Escaping Data Scarcity for High-Resolution Heterogeneous Face Hallucination
• Deepfake检测
  • Detecting Deepfakes with Self-Blended Images
    😮oral⭐code
• 人脸重建
  • JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction
    ⭐code🏠project📰解读
• 人脸捕捉
  • EMOCA: Emotion Driven Monocular Face Capture and Animation
    🏠project
• 换头
  • Few-Shot Head Swapping in the Wild
    😮oral⭐code🏠project📺video📰解读
• 人像畸变矫正
  • Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer
    ⭐code📰解读
• 3D人脸建模
  • Physically-guided Disentangled Implicit Rendering for 3D Face Modeling
    📰解读
• 人脸修复
  • Blind Face Restoration via Integrating Face Shape and Generative Priors
    📰解读

10.3D(三维视觉)

• Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
• Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows
  ⭐code
• 3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
  😮oral⭐code📰解读
• Stereo Merging
  • PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation
  • GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature
    ⭐code
  • Degradation-agnostic Correspondence from Resolution-asymmetric Stereo
  • Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation
    😮oral⭐code📰解读
• 深度估计
  • OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion
  • NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation
  • 🐦️Toward Practical Self-Supervised Monocular Indoor Depth Estimation
  • P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior
    ⭐code
  • HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model
  • Multi-Frame Self-Supervised Depth with Transformers
  • Layered Depth Refinement with Mask Guidance
    🏠project
• 房间布局
  • LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network
    ⭐code📰粗解
• MVS
  • RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo
  • TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers
    ⭐code📰解读
  • Non-parametric Depth Distribution Modelling based Depth Inference for Multi-view Stereo
• 三维重建
  • PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo
  • Self-supervised Neural Articulated Shape and Appearance Models
    🏠project
  • BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion
  • Topologically-Aware Deformation Fields for Single-View 3D Reconstruction
    ⭐code🏠project
  • Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction
    ⭐code🏠project📰解读
  • What's in your hands? 3D Reconstruction of Generic Objects in Hands
    ⭐code🏠project📺video📰解读
  • Surface Reconstruction from Point Clouds by Learning Predictive Context Priors
    ⭐code
  • FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction
    ⭐code
    📰解读
  • 三维场景重建
    • Neural 3D Scene Reconstruction with the Manhattan-world Assumption
      😮oral⭐code🏠project📺video📰解读
  • 手物重建
    • Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution
  • 三维服装网格重建
    • Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images
      🏠project
    • Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing
      🏠project
  • 三维网格重建
    • Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes
      ⭐code📰解读
• 三维形状重建
  • 3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow
  • GIFS: Neural Implicit Function for General Shape Representation
    🏠project
• 三维服装变形
  • SNUG: Self-Supervised Neural Dynamic Garments
    😮oral⭐code
• 纹理迁移与合成
  • AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis
    ⭐code🏠project📺video
• 形状匹配
  • A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching
    ⭐code
  • Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matching
    ⭐code
• 表面重建
  • Critical Regularizations for Neural Surface Reconstruction in the Wild

9.Human Pose Estimation(人体姿态估计)

• COAP: Compositional Articulated Occupancy of People
  ⭐code🏠project📺video📰解读
• Context-Aware Sequence Alignment using 4D Skeletal Augmentation
  😮oral⭐code🏠project
• 多人姿态估计
  • Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation
• 基于视频的HPE
  • Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation
    ::oral:star:code
• 3D pose
  • MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video
  • PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision
    😮oral⭐code
  • Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation
  • Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
    📰精准高效估计多人3D姿态，美图&北航分布感知式单阶段模型
• 4D 人体捕获
  • H4D: Human 4D Modeling by Learning Neural Compositional Representation
• 手势生成
  • Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation
• 3D手网格估计
  • HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network
• 3D形状生成
  • Towards Implicit Text-Guided 3D Shape Generation
  • 3D狗的形状
    • BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information
      🏠project
• 运动捕捉
  • Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture
    🏠project
• 手臂-手部动态估计
  • Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic Estimation
• 3D手重建
  • LISA: Learning Implicit Shape and Appearance of Hands
    🏠project
• 3D人体形状
  • OSSO: Obtaining Skeletal Shape from Outside
    ⭐code🏠project📺video📰解读
• Dense correspondence
  • BodyMap: Learning Full-Body Dense Correspondence Map
    🏠project
• 3D人体运动重建
  • Differentiable Dynamics for Articulated 3d Human Motion Reconstruction
• 三维人体姿态重建
  • Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video

8.Action Detection(人体动作检测与识别)

• 动作检测
  • Colar: Effective and Efficient Online Action Detection by Consulting Exemplars
  • Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos
  • End-to-End Semi-Supervised Learning for Video Action Detection
  • SPAct: Self-supervised Privacy Preservation for Action Recognition
    ⭐code
  • Temporal Alignment Networks for Long-term Video
    😮oral⭐code🏠project📰粗解
  • SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition
  • 零样本动作识别
    • Cross-modal Representation Learning for Zero-shot Action Recognition
      ⭐code
      零样本动作识别：跨模态表示学习
  • 小样本动作识别
    • Hybrid Relation Guided Set Matching for Few-shot Action Recognition
      ⭐code📰解读
  • 时序动作检测
    • An Empirical Study of End-to-End Temporal Action Detection
      ⭐code📰粗解
• 时序动作定位
  • Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation
    ⭐code📰粗解
  • Unsupervised Pre-training for Temporal Action Localization Tasks
    ⭐code
  • ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization
    ⭐code
  • Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization
    ⭐code
  • Structured Attention Composition for Temporal Action Localization
    ⭐code
• 重复动作计数
  • TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting
    😮oral⭐code🏠project
• 组动作识别
  • Dual-AI: Dual-path Action Interaction Learning for Group Activity Recognition
    😮oral
  • Detector-Free Weakly Supervised Group Activity Recognition
• 动作质量评估
  • FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment
    😮oral⭐code🏠project📰解读

7.Point Cloud(点云)

• Shape-invariant 3D Adversarial Point Clouds
  ⭐code
• AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception
• REGTR: End-to-end Point Cloud Correspondences with Transformers
  ⭐code
• Equivariant Point Cloud Analysis via Learning Orientations for Message Passing
  ⭐code
• Text2Pos: Text-to-Point-Cloud Cross-Modal Localization
• Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
  ⭐code
• Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation
  ⭐code📰解读
• 3DeformRS: Certifying Spatial Deformations on Point Clouds
  ⭐code
• Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors
  ⭐code📰解读
• Density-preserving Deep Point Cloud Compression
  ⭐code🏠project📰解读
• Surface Representation for Point Clouds
  😮oral⭐code
  📰解读
• 3D 点云
  • CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding
    ⭐code📰粗解
    CrossPoint，一个用于 3D 点云表征学习的简单自监督学习框架。虽然该方法是在合成的三维物体数据集上训练的，但在下游任务中的实验结果，如三维物体分类和三维物体部分分割，在合成和真实世界的数据集中都证明了该方法在学习可迁移表征方面的有效性。
  • A Unified Query-based Paradigm for Point Cloud Understanding
  • WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation
    ⭐code
  • 3D点云分割
    • Stratified Transformer for 3D Point Cloud Segmentation
      ⭐code
• 点云分类
  • ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation
    ⭐code📰粗解📓
• 点云配准
  • SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
    ⭐code
    📰二阶相似性测度，让传统配准方法取得比深度学习更好的性能，并达到深度学习的速度
• 点云补全
  • Learning a Structured Latent Space for Unsupervised Point Cloud Completion
  • Learning Local Displacements for Point Cloud Completion
  • LAKe-Net: Topology-Aware Point Cloud Completionby Localizing Aligned Keypoints
    📰粗解
• 点云分割
  • Contrastive Boundary Learning for Point Cloud Segmentation
    ⭐code📰解读
  • SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
    ⭐code📰解读
• 场景流估计
  • RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds

6.Object Tracking(目标跟踪)

• TCTrack: Temporal Contexts for Aerial Tracking
  ⭐code📰粗解
  📰TCTrack: 用于空中跟踪的时序信息框架
• Correlation-Aware Deep Tracking
• Global Tracking Transformers
  ⭐code
• Unified Transformer Tracker for Object Tracking
  ⭐code
• Global Tracking via Ensemble of Local Trackers
• Unsupervised Learning of Accurate Siamese Tracking
  ⭐code
• Transformer Tracking with Cyclic Shifting Window Attention
  ⭐code
  Transformer 跟踪：循环为一窗口注意力模型。该算法在五个数据集VOT2020, UAV123, LaSOT, TrackingNet, GOT-10k上均实现了新的SOTA.
• Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos
  ⭐code
• 3D 目标跟踪
  • Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds
    ⭐code📰粗解
• 多目标跟踪
  • Learning of Global Objective for Network Flow in Multi-Object Tracking
  • MeMOT: Multi-Object Tracking with Memory
    😮oral
• RGB-T跟踪
  • Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline
    🏠project📰解读
• 视觉跟踪
  • Ranking-Based Siamese Visual Tracking
    ⭐code📰解读

5.Object Detection(目标检测)

• DN-DETR: Accelerate DETR Training by Introducing Query DeNoising
  ⭐code📰粗解
• Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation
  ⭐code
• Beyond Bounding Box: Multimodal Knowledge Learning for Object Detection
  以往目标检测往往以目标包围框作为标注训练，作者引入语言提示信息，提炼语言知识到目标检测模型中，获得了1.6~2.1%的性能增益。
• Dynamic Sparse R-CNN
• Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild
  ⭐code📰粗解
• Focal and Global Knowledge Distillation for Detectors
  ⭐code📰解读
  关于目标检测的知识蒸馏工作，只需要30行代码就可以在 anchor-base, anchor-free 的单阶段、两阶段各种检测器上稳定涨点，现在代码已经开源。
• Group R-CNN for Weakly Semi-supervised Object Detection with Points
  ⭐code
  📰解读
• Real-time Object Detection for Streaming Perception
  ⭐code📰解读
• Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition
• Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model
  ⭐code
• Optimal Correction Cost for Object Detection Evaluation
• Expanding Low-Density Latent Regions for Open-Set Object Detection
  ⭐code
  📰解读
• SIOD: Single Instance Annotated Per Category Per Image for Object Detection
  📰解读
• Task-specific Inconsistency Alignment for Domain Adaptive Object Detection
  ⭐code
• Zero-Query Transfer Attacks on Context-Aware Object Detectors
• AdaMixer: A Fast-Converging Query-Based Object Detector
  😮oral⭐code
• Learning to Detect Mobile Objects from LiDAR Scans Without Labels
  ⭐code
• Forecasting from LiDAR via Future Object Detection
  ⭐code
• Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection
  😮oral
• Multi-Granularity Alignment Domain Adaptation for Object Detection
• Proper Reuse of Image Classification Features Improves Object Detection
  ⭐code
• R(Det)^2: Randomized Decision Routing for Object Detection
• Towards Robust Adaptive Object Detection under Noisy Annotations
  ⭐code
• Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint
• Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
• Interactive Segmentation and Visualization for Tiny Objects in Multi-megapixel Images
  ⭐code
• Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
  ⭐code
  跨域目标检测：目标感知双分支蒸馏
• Progressive End-to-End Object Detection in Crowded Scenes
  ⭐code
  📰解读
• HCSC: Hierarchical Contrastive Selective Coding
  ⭐code
  📰CNN自监督预训练新SOTA：上交、Mila、字节联合提出具有层级结构的图像表征自学习新框架
• Recurrent Glimpse-based Decoder for Detection with Transformer
  😮oral⭐code
  📰解读
• 小样本目标检测
  • Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection
  • Few-Shot Object Detection with Fully Cross-Transformer
• 目标定位
  • Weakly Supervised Object Localization as Domain Adaption
    ⭐code📰粗解
  • Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
  • Object Localization under Single Coarse Point Supervision
    ⭐code
    📰解读
• 3D目标检测
  • A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation
  • Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving
    ⭐code📰粗解
  • Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
    🏠project
  • Point2Seq: Detecting 3D Objects as Sequences
    ⭐code
  • MonoDETR: Depth-aware Transformer for Monocular 3D Object Detection
    ⭐code
  • LiDAR Snowfall Simulation for Robust 3D Object Detection
    😮oral⭐code
  • CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection
  • Homography Loss for Monocular 3D Object Detection
  • HyperDet3D: Learning a Scene-conditioned 3D Object Detector
  • DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
    ⭐code
  • OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data
    ⭐code
  • Focal Sparse Convolutional Networks for 3D Object Detection
    😮oral⭐code📰解读📓
  • Rotationally Equivariant 3D Object Detection
    🏠project
  • Bridged Transformer for Vision and Point Cloud 3D Object Detection
    📰解读
  • Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion
    📰解读
  • VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention
    ⭐code
    📰华南理工提出VISTA：双跨视角空间注意力机制实现3D目标检测SOTA，即插即用
  • Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection
    😮oral
• 伪装目标检测
  • Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection
    ⭐code
• 全监督目标检测
  • Omni-DETR: Omni-Supervised Object Detection with Transformers
    ⭐code
• 半监督目标检测
  • Dense Learning based Semi-Supervised Object Detection
    ⭐code📰解读
• 显著目标检测
  • Pyramid Grafting Network for One-Stage High Resolution Saliency Detection
    ⭐code📰解读
    📰超高分辨率显著目标检测，新颖高效的错层嫁接架构PGNet（CVPR2022）
  • Learning from Pixel-Level Noisy Label : A New Perspective for Light Field Saliency Detection
    ⭐code📰解读
  • Bi-directional Object-context Prioritization Learning for Saliency Ranking
    ⭐code
• 关键点检测
  • Self-Supervised Equivariant Learning for Oriented Keypoint Detection
  • UKPGAN: A General Self-Supervised Keypoint Detector
    ⭐code
    📰粗解
• Affordance grounding
  • Learning Affordance Grounding from Exocentric Images
    ⭐code📰解读
• 图像对齐
  • Unsupervised Homography Estimation with Coplanarity-Aware GAN
• 物体属性识别
  • Disentangling Visual Embeddings for Attributes and Objects
    😮oral⭐code

4.Image Captioning(图像字幕)

• X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning
• Quantifying Societal Bias Amplification in Image Captioning
• NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models
• It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection
  ⭐code🏠project
• Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning
• Novel Object Captioning
  • NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge

3.Image Progress(图像处理)

• 图像恢复
  • Attentive Fine-Grained Structured Sparsity for Image Restoration
    ⭐code📰解读
• 图像修复
  • Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding
    ⭐code📰粗解
  • MAT: Mask-Aware Transformer for Large Hole Image Inpainting
    ⭐code
  • Reduce Information Loss in Transformers for Pluralistic Image Inpainting
• 图像拼接
  • Deep Rectangling for Image Stitching: A Learning Baseline
    😮oral⭐code📰粗解
• 运动去模糊
  • Unifying Motion Deblurring and Frame Interpolation with Events
• image outpainting
  • Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation
    🏠project
• 图像美学评估
  • Personalized Image Aesthetics Assessment with Rich Attributes
    🏠project
• 图像质量评估
  • Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment
    ⭐code📰解读
• 图像去雨
  • Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond
    ⭐code
• 图像去模糊
  • Learning to Deblur using Light Field Generated and Real Defocus Images
    ⭐code🏠project
• 图像去噪
  • CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Image
    ⭐code
  • NAN: Noise-Aware NeRFs for Burst-Denoising
• De-rendering
  • Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata
    ⭐code📰解读
• 图像增强
  • Toward Fast, Flexible, and Robust Low-Light Image Enhancement
    😮oral⭐code📰解读
  • AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement
    ⭐code
  • Directional Self-supervised Learning for Heavy Image Augmentations
    📰解读
• 图像和谐化
  • SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization
    ⭐code
• 图像超级补全
  • Scene Graph Expansion for Semantics-Guided Image Outpainting
    该文解决了一个非常有意思的问题，通过对图像场景图的扩展，对图像边缘以外的内容进行语义引导的内容生成，可帮助设计师快速绘就自然和谐的图像扩展内容。
• 语义图像匹配
  • TransforMatcher: Match-to-Match Attention for Semantic Correspondence
    📰解读

2.Image Segmentation(图像分割)

• FocalClick: Towards Practical Interactive Image Segmentation
  ⭐code📰粗解
• Semantic-Aware Domain Generalized Segmentation
  😮oral⭐code
• ReSTR: Convolution-free Referring Image Segmentation Using Transformers
• Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation
  🏠project
  全景神经场：谷歌新提出的语义级目标感知的神经场景表示模型。该表示模型可以有效地用于新视图合成、2D 全景分割、3D 场景编辑和多视图深度预测等多项任务。相信这又会是一个引领潮流的新方向。
• 实例分割
  • E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
    ⭐code📰粗解
  • Sparse Instance Activation for Real-Time Instance Segmentation
    ⭐code
  • SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation
    🏠project
  • Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity
    ⭐code🏠project
  • DArch: Dental Arch Prior-assisted 3D Tooth Instance Segmentation
  • Relieving Long-tailed Instance Segmentation via Pairwise Class Balance
    ⭐code📰解读
  • ContrastMask: Contrastive Learning to Segment Every Thing
    📰解读
    基于像素级对比学习的不完全监督实例分割算法
  • 半监督实例分割
    • Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?
  • 3D 实例分割
    • SoftGroup for 3D Instance Segmentation on Point Clouds
      ⭐code📰粗解
  • 🐦️FreeSOLO: Learning to Segment Objects without Annotations
• 语义分割
  • Pin the Memory: Learning to Generalize Semantic Segmentation
    ⭐code📰解读
  • Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation
    ⭐code📰解读
  • GroupViT: Semantic Segmentation Emerges from Text Supervision
    ⭐code🏠project📺video
    📰做语义分割不用任何像素标签，UCSD、英伟达在ViT中加入分组模块
  • Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation
    ⭐code📰粗解
  • Deep Hierarchical Semantic Segmentation
    ⭐code
  • Semantic Segmentation by Early Region Proxy
    ⭐code📰粗解
  • SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation
    ⭐code
  • Rethinking Semantic Segmentation: A Prototype View
    😮oral⭐code
  • On the Road to Online Adaptation for Semantic Image Segmentation
  • Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds
  • NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Night
    ⭐code📰解读
  • TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation
  • Cross-Image Relational Knowledge Distillation for Semantic Segmentation
    ⭐code📰解读
  • Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation
  • Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers
    ⭐code
  • Self-Supervised Learning of Object Parts for Semantic Segmentation
  • Cross-view Transformers for real-time Map-view Semantic Segmentation
    😮oral⭐code
  • Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization
    🏠project
  • Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
    ⭐code📰解读
  • 3D分割
    • MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
      🏠project
    • Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation
      😮oral⭐code📰解读
  • 弱监督语义分割
    • Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation
      ⭐code📰粗解
    • Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation
      ⭐code
    • Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation
      ⭐code
    • Cross Language Image Matching for Weakly Supervised Semantic Segmentation
      ⭐code
    • Multi-class Token Transformer for Weakly Supervised Semantic Segmentation
      ⭐code
    • Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers
      ⭐code📰解读
    • Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
      ⭐code📰粗解
    • L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation
      ⭐code
  • 半监督语义分割
    • Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
    • Semi-supervised Semantic Segmentation with Error Localization Network
      ⭐code🏠project📰粗解
    • UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation
  • 域适应语义分割
    • Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation
      ⭐code
  • 域泛化语义分割
    • WildNet: Learning Domain Generalized Semantic Segmentation from the Wild
      ⭐code
  • 小样本语义分割
    • Learning Non-target Knowledge for Few-shot Semantic Segmentation
      ⭐code
      📰解读
• 动作分割
  • Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos
• 场景解析
  • FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing
    ⭐code
• 雾景分割
  • FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation
    😮oral
• 全景分割
  • Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation
  • Joint Forecasting of Panoptic Segmentations with Difference Attention
    ⭐code📰解读
  • PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation
    ⭐code📰解读
• 抠图
  • Human Instance Matting via Mutual Guidance and Multi-Instance Refinement
    😮oral⭐code

1.其它

• Learning to Anticipate Future with Dynamic Context Removal
  ⭐code📰粗解
• Learning Optimal K-space Acquisition and Reconstruction using Physics-Informed Neural Networks
• Instance-wise Occlusion and Depth Orders in Natural Scenes
• IFOR: Iterative Flow Minimization for Robotic Object Rearrangement
  🏠project
• PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence
  ⭐code🏠project📺video📰粗解
• CAFE: Learning to Condense Dataset by Aligning Features
  ⭐code📰粗解
• Enhancing Adversarial Robustness for Deep Metric Learning
• BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
  ⭐code📰粗解📓
• ACVNet: Attention Concatenation Volume for Accurate and Efficient Stereo Matching
  ⭐code📰粗解
• Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values
  ⭐code
• Do Explanations Explain? Model Knows Best
  ⭐code
• HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
• E-CIR: Event-Enhanced Continuous Intensity Recovery
  ⭐code
• 🐦️Transferability Estimation using Bhattacharyya Class Separability
• Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks
  ⭐code
• GlideNet: Global, Local and Intrinsic based Dense Embedding NETwork for Multi-category Attributes Prediction
  ⭐code
• Differentially Private Federated Learning with Local Regularization and Sparsification
• Towards Efficient and Scalable Sharpness-Aware Minimization
• DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos
• Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences
  ⭐code📰粗解
• Dynamic Dual-Output Diffusion Models
• Moving Window Regression: A Novel Approach to Ordinal Regression
• Egocentric Prediction of Action Target in 3D
• Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning
  ⭐code
• Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction
  ⭐code
• Neural Reflectance for Shape Recovery with Shadow Handling
  ⭐code
• DyRep: Bootstrapping Training with Dynamic Re-parameterization
  ⭐code
• Enhancing Classifier Conservativeness and Robustness by Polynomiality
• Versatile Multi-Modal Pre-Training for Human-Centric Perception
  ⭐code
• Attributable Visual Similarity Learning
  ⭐code
• Optimizing Elimination Templates by Greedy Parameter Search
• Partially Does It: Towards Scene-Level FG-SBIR with Partial Input
• Bi-level Doubly Variational Learning for Energy-based Latent Variable Models
• Brain-inspired Multilayer Perceptron with Spiking Neurons
• ARCS: Accurate Rotation and Correspondence Search
  ⭐code
• iPLAN: Interactive and Procedural Layout Planning
• HINT: Hierarchical Neuron Concept Explainer
  ⭐code
• Visual Abductive Reasoning
  ⭐code
• A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration
  ⭐code
• Learning Structured Gaussians to Approximate Deep Ensembles
• Self-Supervised Image Representation Learning with Geometric Set Consistency
• Balanced Multimodal Learning via On-the-fly Gradient Modulation
  😮oral⭐code
• CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
  ⭐code
• Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation
  😮oral
• Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian
• Long-term Visual Map Sparsification with Heterogeneous GNN
• Clean Implicit 3D Structure from Noisy 2D STEM Images
• Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
• CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism
  ⭐code🏠project
• Fast Light-Weight Near-Field Photometric Stereo
• Fast, Accurate and Memory-Efficient Partial Permutation Synchronization
• Multi-Robot Active Mapping via Neural Bipartite Graph Matching
• Learning Program Representations for Food Images and Cooking Recipes
  😮oral
• Iterative Deep Homography Estimation
  ⭐code
• Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain
• Generating High Fidelity Data from Low-density Regions using Diffusion Models
• Continuous Scene Representations for Embodied AI
  ⭐code🏠project
• It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
• End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps
• Reflection and Rotation Symmetry Detection via Equivariant Learning
• Exploiting Explainable Metrics for Augmented SGD
• On the Importance of Asymmetry for Siamese Representation Learning
  ⭐code
• Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression
• Perception Prioritized Training of Diffusion Models
  ⭐code
• LASER: LAtent SpacE Rendering for 2D Visual Localization
  😮oral
• Efficient Maximal Coding Rate Reduction by Variational Forms
• Exemplar-bsaed Pattern Synthesis with Implicit Periodic Field Network
• Progressive Minimal Path Method with Embedded CNN
• Online Convolutional Re-parameterization
  ⭐code
• Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes
• Leveraging Equivariant Features for Absolute Pose Regression
• Neural Convolutional Surfaces
  🏠project
• GLASS: Geometric Latent Augmentation for Shape Spaces
  ⭐code🏠project
• Total Variation Optimization Layers for Computer Vision
• Identifying Ambiguous Similarity Conditions via Semantic Matching
  ⭐code📰解读
• TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates
• Gravitationally Lensed Black Hole Emission Tomography
  ⭐code🏠project📺video
• Robust and Accurate Superquadric Recovery: a Probabilistic Approach
  ⭐code
• Projective Manifold Gradient Layer for Deep Rotation Regression
  ⭐code
• Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale
  ⭐code
• Single-Photon Structured Light
• Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention
  😮oral⭐code
• Defensive Patches for Robust Recognition in the Physical World
  ⭐code📰解读
• Event-aided Direct Sparse Odometry
  😮oral⭐code🏠project📺video
• Deep Unlearning via Randomized Conditionally Independent Hessians
  ⭐code
• Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data
• Towards Data-Free Model Stealing in a Hard Label Setting
  ⭐code🏠project
• Proto2Proto: Can you recognize the car, the way I do?
  ⭐code
• Balanced MSE for Imbalanced Visual Regression
  😮oral⭐code
  📰CVPR 2022 (Oral) | 回归标签不平衡? 试试Balanced MSE
• Leveraging Unlabeled Data for Sketch-based Understanding
• Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction
  ⭐code🏠project
• Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
  ⭐code📰解读
• RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality
  ⭐code📰解读
• An Image Patch is a Wave: Quantum Inspired Vision MLP
  😮oral⭐code
• A ConvNet for the 2020s
  ⭐code
• NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations
  头发建模：仅用一幅图像，构建高保真度的头发模型，使用隐式神经表示的方法。出自浙大CAD&CG组、ETH Zurich、香港城市大学。
• A Unified Framework for Implicit Sinkhorn Differentiation
  ⭐code
  📰解读
• Towards Better Understanding Attribution Methods
  ⭐code
• Universal Photometric Stereo Network using Global Lighting Contexts
  ⭐code🏠project📺video📰解读

论文尚未公布

• 相机重定位

  • ❌[SceneSqueezer: Learning to Compress Scene for Camera Relocalization]
    😮oral

• 相机成像

  • ❌[Learning to Zoom Inside Camera Imaging Pipeline]
    

• Homography Estimation(旋转估计)

  • ❌[Unsupervised Homography Estimation with Coplanarity-Aware GAN]
    ⭐code📰解读

• 3D人体重建

  • ❌[Putting People in their Place: Monocular Regression of 3D People in Depth]
    ⭐code📰解读

• 图像字幕

  • ❌[Comprehending and Ordering Semantics for Image Captioning]
    📰解读

• 图像去雾

  • ❌[Self-augmented Unpaired Image Dehazing via Density and Depth Decomposition]
    📰解读

• 图像到图像翻译

  • ❌[Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint]
    📰解读

• 光流

  • ❌[Learning Optical Flow with Kernel Patch Attention]
    ⭐code📰解读

• 图像生成

  • ❌[Modeling Image Composition for Complex Scene Generation]
    📰解读

• 连续学习

  • ❌[Continual Learning with Lifelong Vision Transformer]
    📰解读

• 元学习

  • ❌[Learning to Learn and Remember Super Long Multi-Domain Task Sequence]
    📰解读

• 目标检测

  • ❌[Voxel Field Fusion for 3D Object Detection]
    📰解读
  • ❌[ISNet: Shape Matters for Infrared Small Target Detection]
    📰解读

• HOI

  • ❌[Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection]
    📰解读

• 视频建模

  • ❌[Stand-Alone Inter-Frame Attention in Video Models]
    📰解读

• 其他

  • ❌[RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging]
    ⭐code
  • ❌[Learning to Collaborate in Decentralized Learning of Personalized Models]
    📰解读
  • ❌[MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing]
    📰解读

• 视频场景分割

  • ❌[Scene Consistency Representation Learning for Video Scene Segmentation]
    📰解读

• 图像字幕

  • ❌[DIFNet: Boosting Visual Information Flow for Image Captioning]
    📰解读

• 姿态

  • ❌[Location-Free Human Pose Estimation]
    📰解读

• 小样本

  • ❌[Ranking-Guided Distance Calibration for Cross-Domain Few-Shot Learning]
    📰解读
  • ❌[En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning]
    📰解读

• 点云

  • ❌[Surface Representation for Point Clouds]
    📰解读
  • ❌[Deterministic Point Cloud Registration via Novel Transformation Decomposition]
    📰解读

• 人脸

  • ❌[Evaluation-oriented Knowledge Distillation for Deep Face Recognition]
    📰解读
  • ❌[End-to-End Reconstruction-Classification Learning for Face Forgery Detection]
    📰解读

• 目标检测

  • ❌[Thinking Camouflaged Object Detection in Frequency]
    📰解读

• 对抗

  • ❌[Efficent Data-free Model Stealing for Black-box Adversarial Attacks]
    📰解读

• 分割

  • ❌[ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-high Resolution Segmentation]
    📰解读
  • ❌[HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization]
    📰解读

• 3D场景

  • ❌[Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes]
    📰粗解

• 行人轨迹预测

  • ❌[Human Trajectory Prediction with Momentary Observation]
    📰粗解

AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval

ID:Cyelie multi-Variate Function for self-supervised image denoising by disentangling noise form image

Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation

来源
[Two Systems in Thinking: Dual-System Transformer for Grounded Situation Recognition]
[Autoregressive Image Generation using Residual Quantization]
✔️Instance-wise Occlusion and Depth Orders in Natural Scenes
[Style Neophile: Constantly Seeking Novel Styles for Domain Generalization]
[ReSTR: Convolution-free Referring Image Segmentation Using Transformers]
[FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation]
[TransforMatcher: Match-to-Match Attention for Semantic Correspondence]
[Reflection and Rotation Symmetry Detection via Equivariant Learning]
[Semi-supervised Semantic Segmentation with Error Localization Network]
[Future Transformer for Long-term Action Anticipation]
[Self-Taught Metric Learning without Labels]
✔️Fast Point Transformer
[Integrative Few-Shot Learning for Classification and Segmentation]
[Scene Painting via Semantic Image Synthesis]
[Detector-Free Weakly Supervised Group Activity Recognition]

扫码CV君微信（注明：CVPR）入微信交流群：