官网链接：

↘️CVPR-2023-Papers ↘️WACV-2023-Papers

↘️CVPR-2022-Papers ↘️WACV-2022-Papers ↘️ECCV-2022-Papers

↘️ICCV-2021-Papers ↘️CVPR-2021-Papers

↘️CVPR-2020-Papers ↘️ECCV-2020-Papers

• A Unified HDR Imaging Method with Pixel and Patch Level
• SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders
• Bitstream-Corrupted JPEG Images are Restorable: Two-stage Compensation and Alignment Framework for Image Restoration
  ⭐code
• Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement
• DCFace: Synthetic Face Generation with Dual Condition Diffusion Model
  ⭐code
• DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection

• Learning Anchor Transformations for 3D Garment Animation
  ⭐code
• Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion
  ⭐code
• Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion
  ⭐code
• CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decomposition
  🏠project

• Hierarchical Fine-Grained Image Forgery Detection and Localization
  ⭐code
• Detecting and Grounding Multi-Modal Media Manipulation
  ⭐code
  ⭐code虚假信息检测

• Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning
  ⭐code

• Re-thinking Federated Active Learning based on Inter-class Diversity
• Box-Level Active Detection
  ⭐code

• DivClust: Controlling Diversity in Deep Clustering
• MVC
  • On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering
    ⭐code

• Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision
  ⭐code

• Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry
  ⭐code

• edge detection
  • The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector
    ⭐code

• 缺陷定位
  • PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow
• 工业异常检测
  • Multimodal Industrial Anomaly Detection via Hybrid Fusion
    ⭐code

• Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger
• Context-Based Trit-Plane Coding for Progressive Image Compression
  ⭐code
• Learned Image Compression with Mixed Transformer-CNN Architectures
  ⭐code
• 视频压缩
  • Towards Scalable Neural Representation for Diverse Videos
  • HNeRV: A Hybrid Neural Representation for Videos
    ⭐code
    ⭐code

• NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer
  🏠project
• FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization
  🏠project
• StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields
  🏠project
• Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention
  ⭐code
• WildLight: In-the-wild Inverse Rendering with a Flashlight
  ⭐code
• Grid-guided Neural Radiance Fields for Large Urban Scenes
  ⭐code
• GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images
• HandNeRF: Neural Radiance Fields for Animatable Interacting Hands
• ABLE-NeRF: Attention-Based Rendering with Learnable Embeddings for Neural Radiance Field
• NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects
  ⭐code
• JAWS: Just A Wild Shot for Cinematic Transfer in Neural Radiance Fields
  🏠project
• FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views
  ⭐code
• NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination
• MonoHuman: Animatable Human Neural Field from Monocular Video
  ⭐code
• [PlenVDB: A Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering]
  🏠project论文未公开
  在 iPhone12 手机上达到了对于输出 1280x720 分辨率的画面每秒 30 帧的速率。
• Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos
  ⭐code

• NeRF-Gaze: A Head-Eye Redirection Parametric Model for Gaze Estimation

• 扬声器检测
  • A Light Weight Model for Active Speaker Detection
    ⭐code
• 视听语音识别
  • Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring
    ⭐code
  • AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR
  • SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision
• 视听定位
  • Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning
    ⭐code
  • Audio-Visual Grouping Network for Sound Localization from Mixtures
    ⭐code
• 音频源分离
  • Language-Guided Audio-Visual Source Separation via Trimodal Consistency
• 声音合成
  • Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos
    ⭐code
• 电影音频描述
  • AutoAD: Movie Description in Context
    🏠project
• 从声音中生成场景图像
  • Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment

• Frequency-Modulated Point Cloud Rendering with Easy Editing
  ⭐code
• Balanced Spherical Grid for Egocentric View Synthesis
• Progressively Optimized Local Radiance Fields for Robust View Synthesis
  ⭐code
• F$^{2}$-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories
  ⭐code
• Enhanced Stable View Synthesis
• Consistent View Synthesis with Pose-Guided Diffusion Models
  ⭐code

• xFBD: Focused Building Damage Dataset and Analysis
  建筑物损坏数据集
• Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo
  🌻dataset
• Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes
• HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling
  🌻dataset
• CUDA: Convolution-based Unlearnable Datasets
  🌻dataset
• MVImgNet: A Large-scale Dataset of Multi-view Images
  🌻dataset
• V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception
  🌻dataset
  Vehicle-to-Vehicle(V2V)感知
• Polynomial Implicit Neural Representations For Large Diverse Datasets
  🌻dataset
• MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset
  🌻dataset
• RaBit: Parametric Modeling of 3D Biped Cartoon Characters with a Topological-consistent Dataset
  🌻dataset
• Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline
• Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts
  ⭐code
• ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data
  ⭐code
• CelebV-Text: A Large-Scale Facial Text-Video Dataset
  ⭐code
  人脸文本到视频生成
• Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method
  ⭐code
  艺术图像美学评估
• GeoNet: Benchmarking Unsupervised Adaptation across Geographies
  ⭐code
• PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout
  ⭐code
• CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
  🏠project
  攀爬动作数据集
• Uncurated Image-Text Datasets: Shedding Light on Demographic Bias
• AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection
  ⭐code
  🏠project公共短视频镜头边界检测数据集

• 手语识别
  • Continuous Sign Language Recognition with Correlation Network
    ⭐code
  • Natural Language-Assisted Sign Language Recognition
    ⭐code
• 手语检索
  • CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning
    ⭐code

• EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning
  ⭐code
• DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback

• DyLiN: Making Light Field Networks Dynamic
  ⭐code
• Learning Rotation-Equivariant Features for Visual Correspondence
  🏠project

• Diversity-Measurable Anomaly Detection
• SimpleNet: A Simple Network for Image Anomaly Detection and Localization
  ⭐code
• WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
• OOD
  • Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection
    ⭐code
  • LINe: Out-of-Distribution Detection by Leveraging Important Neurons

• Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes

• Text-Visual Prompting for Efficient 2D Temporal Video Grounding

• DG
  • Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View
  • Improved Test-Time Adaptation for Domain Generalization
    ⭐code
  • Modality-Agnostic Debiasing for Single Domain Generalization
  • Neuron Structure Modeling for Generalizable Remote Physiological Measurement
    ⭐code
  • Sharpness-Aware Gradient Matching for Domain Generalization
    ⭐code
  • Improving Generalization with Domain Convex Game
  • Generalist: Decoupling Natural and Robust Generalization
    ⭐code
  • ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization
    ⭐code
  • Progressive Random Convolutions for Single Domain Generalization
  • Meta-causal Learning for Single Domain Generalization
• DA
  • Guiding Pseudo-labels with Uncertainty Estimation for Test-Time Adaptation
    ⭐code
  • DATE: Domain Adaptive Product Seeker for E-commerce
    ⭐code
  • Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective
  • Upcycling Models under Domain and Category Shift
    ⭐code
  • C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation
  • A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation
    ⭐code
  • TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation
    ⭐code
  • [OSAN: A One-Stage Alignment Network to Unify Multimodal Alignment and Unsupervised Domain Adaptation]域适应(论文未公开)
  • Feature Alignment and Uniformity for Test Time Adaptation
• ZSL
  • Bi-directional Distribution Alignment for Transductive Zero-Shot Learning
    ⭐code
  • Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning
    ⭐code
  • Learning Attention as Disentangler for Compositional Zero-shot Learning
    ⭐code
  • Zero-shot Model Diagnosis

• Prototype-based Embedding Network for Scene Graph Generation
  ⭐code
• Devil's on the Edges: Selective Quad Attention for Scene Graph Generation
  🏠project

• DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction
• Ensemble-based Blackbox Attacks on Dense Prediction
  ⭐code
• Probabilistic Prompt Learning for Dense Prediction
• 密集检测
  • One-to-Few Label Assignment for End-to-End Dense Detection
    ⭐code

• Make Landscape Flatter in Differentially Private Federated Learning
• The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning

• Advancing Deep Metric Learning Through Multiple Batch Norms And Multi-Targeted Adversarial Examples

• 类增量学习
  • Dense Network Expansion for Class Incremental Learning
  • Class-Incremental Exemplar Compression for Class-Incremental Learning
    ⭐code
  • Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning
    ⭐code
  • On the Stability-Plasticity Dilemma of Class-Incremental Learning

• Feature Separation and Recalibration for Adversarial Robustness
  ⭐code
• CFA: Class-wise Calibrated Fair Adversarial Training
  ⭐code
• 黑盒
  • BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning
    ⭐code
  • Reinforcement Learning-Based Black-Box Model Inversion Attacks
• 对抗样本
  • Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression
  • Improving the Transferability of Adversarial Samples by Path-Augmented Method
• 后门攻击
  • Single Image Backdoor Inversion via Robust Smoothed Classifiers
    ⭐code
  • Backdoor Defense via Adaptively Splitting Poisoned Dataset
    ⭐code
  • Detecting Backdoors in Pre-trained Encoders
    ⭐code
• 对抗攻击
  • Adversarial Attack with Raindrops
  • Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization
  • Re-thinking Model Inversion Attacks Against Deep Neural Networks
    ⭐code
  • Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning
    ⭐code

• Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning
  ⭐code
• Computationally Budgeted Continual Learning: What Does Matter?
  ⭐code
• Preserving Linear Separability in Continual Learning by Backward Feature Projection
• [Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling]持续学习(论文未公开)
• Exploring Data Geometry for Continual Learning
• PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning

• Meta-Learning with a Geometry-Adaptive Preconditioner
  ⭐code元学习

• Twin Contrastive Learning with Noisy Labels
  ⭐code
• Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens

• Rethinking Optical Flow from Geometric Matching Consistent Perspective
  ⭐code
• DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling
• AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representation

• 场景文本检测
  • Turning a CLIP Model into a Scene Text Detector
    ⭐code
  • Towards Unified Scene Text Spotting based on Sequence Generation
    ⭐code
• 表格结构识别
  • Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
• 字体生成
  • CF-Font: Content Fusion for Few-shot Font Generation
    ⭐code
• 手写文本生成
  • Disentangling Writer and Character Styles for Handwriting Generation
    ⭐code
  • Handwritten Text Generation from Visual Archetypes
• 矢量字体合成
  • DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality
    ⭐code
• 生成图形文档
  • Towards Flexible Multi-modal Document Models
    ⭐code

• Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks
  ⭐code
• 量化
  • Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
    ⭐code
• 剪枝
  • CP$^3$: Channel Pruning Plug-in for Point-based Networks
• MC
  • Hard Sample Matters a Lot in Zero-Shot Quantization
• KD
  • DisWOT: Student Architecture Search for Distillation WithOut Training
    ⭐code
  • KD-DLGAN: Data Limited Image Generation via Knowledge Distillation
  • Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning

• Detecting Human-Object Contact in Images
  🏠project
• Category Query Learning for Human-Object Interaction Classification
• Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention
• Relational Context Learning for Human-Object Interaction Detection
• HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models
  ⭐code
• Visibility Aware Human-Object Interaction Tracking from Single RGB Camera
  🏠project
• Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream
• 双手交互
  • Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes
    ⭐code
• 手物交互
  • Visual-Tactile Sensing for In-Hand Object Reconstruction
    🏠project
  • CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis
    ⭐code

• Full or Weak annotations? An adaptive strategy for budget-constrained annotation campaigns
• 关键点定位
  • Few-shot Geometry-Aware Keypoint Localization
    ⭐code

• FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks
  ⭐code
• DeAR: Debiasing Vision-Language Models with Additive Residuals
• Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning
• Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding
  ⭐code
• VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining
• MAGVLT: Masked Generative Vision-and-Language Transformer
• Visual-Language Prompt Tuning with Knowledge-guided Context Optimization
• Top-Down Visual Attention from Analysis by Synthesis
  🏠project
• Accelerating Vision-Language Pretraining with Free Language Modeling
  ⭐code
• Multi-Modal Representation Learning with Text-Driven Soft Masks
• Fine-tuned CLIP models are efficient video learners
  ⭐code
• MaPLe: Multi-modal Prompt Learning
  ⭐code
• Learning to Name Classes for Vision and Language Models
• Clover: Towards A Unified Video-Language Alignment and Fusion Model
  ⭐code
  Clover 视频-文本预训练模型在 DiDeMo、MSRVTT 和 LSMDC 三个文本-视频检索任务上取得了 zero-shot 及 finetune performance 的最佳表现；在 8 个主流的视频问答 benchmark 上也达到了新的 state-of-the-art。
• VLN
  • Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding
    🏠project
  • Lana: A Language-Capable Navigator for Instruction Following and Generation
    ⭐code
  • KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation
    ⭐code
  • Improving Vision-and-Language Navigation by Generating Future-View Image Semantics
    ⭐code

• VQA
  • SimVQA: Exploring Simulated Environments for Visual Question Answering
    🏠project
  • MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering
  • Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering
    ⭐code
  • MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos
  • Divide and Conquer: Answering Questions with Object Factorization and Compositional Reasoning
    ⭐code

• 机器人
  • PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations
  • Learning Human-to-Robot Handovers from Point Clouds
    ⭐code
  • Neural Volumetric Memory for Visual Locomotion Control
    ⭐code
  • 机器手抓取
    • UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
      🏠project
    • UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning
  • Visual Navigation(视觉导航)
    • Renderable Neural Radiance Map for Visual Navigation
• SLAM
  • Efficient Map Sparsification Based on 2D and 3D Discretized Grids
    ⭐code
• 虚拟试穿
  • GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning
    ⭐code
• AR/VR
  • Affordance Grounding from Demonstration Video to Target Image
    ⭐code
  • Learning to Zoom and Unzoom
    ⭐code
• Visual Localization(视觉定位)
  • OrienterNet: Visual Localization in 2D Public Maps with Neural Matching
  • Visual Localization using Imperfect 3D Models from the Internet

• CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer
• StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer
  ⭐code
• Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer
  ⭐code

• 物体计数
  • Zero-shot Object Counting
    ⭐code
• 物体重识别
  • MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID
    ⭐code
  • Large-scale Training Data Search for Object Re-identification
    ⭐code
  • Adaptive Sparse Pairwise Loss for Object Re-Identification
    ⭐code
• 物体姿势估计
  • Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation
  • HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation
  • TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation
    🏠project
• 6D
  • Rigidity-Aware Detection for 6D Object Pose Estimation
• 动物姿态估计
  • ScarceNet: Animal Pose Estimation with Scarce Annotations

• Equiangular Basis Vectors
  ⭐code
• Improving Image Recognition by Retrieving from Web-Scale Image-Text Data
• Boosting Verified Training for Robust Image Classifications via Abstraction
  ⭐code
• Semantic Prompt for Few-Shot Image Recognition
• Regularization of polynomial networks for image recognition
  ⭐code
• Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm
  ⭐code
• Dynamic Conceptional Contrastive Learning for Generalized Category Discovery
  ⭐code
• 小样本分类
  • Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners
    ⭐code
  • Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings
    ⭐code
• 细粒度
  • Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems
    ⭐code
  • Fine-Grained Classification with Noisy Labels
• 长尾分类
  • Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification
• 长尾视觉识别
  • SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail
  • Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation
• 多标签分类
  • Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification
    ⭐code
• 多视觉分类
  • Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification

• ISR
  • OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution
  • CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input
  • Super-Resolution Neural Operator
    ⭐code
  • Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution
  • Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution
  • Human Guided Ground-truth Generation for Realistic Image Super-resolution
    ⭐code
  • Implicit Diffusion Models for Continuous Super-Resolution
  • [Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution]超分辨率(论文未公开)
• VSR
  • Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting
    ⭐code
• 文本图像超分辨率
  • Learning Generative Structure Prior for Blind Text Image Super-resolution
    ⭐code

• 基于草图的图像检索
  • Data-Free Sketch-Based Image Retrieval
    ⭐code
  • CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not
  • Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR
    ⭐code
  • Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style
    ⭐code
• 文本-视频检索
  • Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
    ⭐code

• Freestyle Layout-to-Image Synthesis
  ⭐code
• Few-shot Semantic Image Synthesis with Class Affinity Transfer图像合成
• Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
  ⭐code
• TopNet: Transformer-based Object Placement Network for Image Compositing
• 基于草图生成
  • Picture that Sketch: Photorealistic Image Generation from Abstract Sketches
    🏠project
• 图像-视频合成
  • Conditional Image-to-Video Generation with Latent Flow Diffusion Models
    ⭐code
• 海报生成
  • Unsupervised Domain Adaption with Pixel-level Discriminator for Image-aware Layout Generation
• 文本-图像合成
  • Variational Distribution Learning for Unsupervised Text-to-Image Generation
  • Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
  • Shifted Diffusion for Text-to-image Generation
    ⭐code
• prompting
  • Diversity-Aware Meta Visual Prompting
    ⭐code
• 生成
  • LayoutDM: Discrete Diffusion Model for Controllable Layout Generation
    🏠project
  • Controllable Mesh Generation Through Sparse Latent Point Diffusion Models
    🏠project
  • DiffCollage: Parallel Generation of Large Content with Diffusion Models
    🏠project
  • LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation
    ⭐code

• MethaneMapper: Spectral Absorption aware Hyperspectral Transformer for Methane Detection
• 图像检测
  • Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images
    ⭐code

• 自动驾驶
  • Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving
  • GINA-3D: Learning to Generate Implicit Neural Assets in the Wild自动驾驶
• 轨迹预测
  • IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction
  • Leapfrog Diffusion Model for Stochastic Trajectory Prediction
    ⭐code
  • Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction
    ⭐code
  • FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory Prediction
  • Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction
• Place Recognition
  • Data-efficient Large Scale Place Recognition with Graded Similarity Supervision
    ⭐code
  • R2Former: Unified Retrieval and Reranking Transformer for Place Recognition
    ⭐code

• PA&DA: Jointly Sampling PAth and DAta for Consistent NAS
  ⭐code

• 人员检索
  • Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval
    ⭐code
• 可见光-红外人员重识别(VIReID)
  • Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification
    ⭐code
  • Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification
  • PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification可见光-红外人员重识别(VI-ReID)
• 行人检测
  • VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision
    ⭐code
• 人群计数
  • CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
    ⭐code

• Towards Trustable Skin Cancer Diagnosis via Rewriting Model’s Decision
• Hierarchical discriminative learning improves visual representations of biomedical microscopy
  🏠project
• Topology-Guided Multi-Class Cell Context Generation for Digital Pathology
• Image Quality-aware Diagnosis via Meta-knowledge Co-embedding
• METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens医学诊断
• 3D医学
  • Geometric Visual Similarity Learning in 3D Medical Image Self-supervised Pre-training
    ⭐code
• 图像配准
  • Indescribable Multi-modal Spatial Evaluator
    ⭐code
• 图像分类
  • ask-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification
    ⭐code
• 报告生成
  • Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation
    ⭐code
• 医学影像分割
  • Orthogonal Annotation Benefits Barely-supervised Medical Image Segmentation
  • Fair Federated Medical Image Segmentation via Client Contribution Estimation
  • Devil is in the Queries: Advancing Mask Transformers for Real-world Medical Image Segmentation and Out-of-Distribution Localization
  • Weakly supervised segmentation with point annotations for histopathology images via contrast-based variational model
• 医学影像分析
  • Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data
  • Directional Connectivity-based Segmentation of Medical Images
    ⭐code
• 肿瘤分割
  • Label-Free Liver Tumor Segmentation

• 无监督学习
  • Non-Contrastive Unsupervised Learning of Physiological Signals from Video
    ⭐code
• 自监督
  • Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning
  • Correlational Image Modeling for Self-Supervised Visual Pre-Training
  • Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks
    ⭐code
    👍CVPR 2023 深挖无标签数据价值！自监督学习框架SOLIDER：用于以人为中心的视觉
  • Mixed Autoencoder for Self-supervised Visual Representation Learning
  • Siamese DETR
    ⭐code
  • Token Boosting for Robust Self-Supervised Visual Transformer Pre-training
• 半监督
  • Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data
    ⭐code
  • ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning

• Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves
  🏠project
• AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images
  ⭐code
• Generic-to-Specific Distillation of Masked Autoencoders
  ⭐code
• BiFormer: Vision Transformer with Bi-Level Routing Attention
  ⭐code
• Making Vision Transformers Efficient from A Token Sparsification View
• Dual-path Adaptation from Image to Video Transformers
  ⭐code
• Spherical Transformer for LiDAR-based 3D Recognition
  ⭐code
• MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
  ⭐code
• Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers
• Learning Expressive Prompting With Residuals for Vision Transformers
• SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer
  🏠project
• Visual Dependency Transformers: Dependency Tree Emerges from Reversed AttentionTransformer
• Token Boosting for Robust Self-Supervised Visual Transformer Pre-trainingTransformer
• Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention
  ⭐code
• RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer
  ⭐code
• DropKey
  👍CVPR 2023｜两行代码高效缓解视觉Transformer过拟合，美图&国科大联合提出正则化方法DropKey

• Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos
  ⭐code
• VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
• Implicit View-Time Interpolation of Stereo Videos using Multi-Plane Disparities and Non-Uniform Coordinates
  🏠project
  🏠project
• 视频时刻检索
  • Towards Generalisable Video Moment Retrieval:Visual-Dynamic Injection to Image-Text Pre-Training
  • Query-Dependent Video Representation for Moment Retrieval and Highlight Detection
    ⭐code
  • Hierarchical Video-Moment Retrieval and Step-Captioning
    ⭐code
• 视频高亮检测
  • Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies
    ⭐code
• 视频帧插值
  • Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
    ⭐code
  • Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time
    ⭐code
  • BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation
    ⭐code视频帧插值
• 视频合成
  • Decomposed Diffusion Models for High-Quality Video Generation
• 视频预测
  • MOSO: Decomposing MOtion, Scene and Object for Video Prediction
    ⭐code
  • A Dynamic Multi-Scale Voxel Flow Network for Video Prediction
    ⭐code
• 视频理解
  • Selective Structured State-Spaces for Long-Form Video Understanding
  • How you feelin'? Learning Emotions and Mental States in Movie Scenes
    ⭐code
  • System-status-aware Adaptive Network for Online Streaming Video Understanding
  • Streaming Video Model
    ⭐code
  • Procedure-Aware Pretraining for Instructional Video Understanding
    ⭐code
  • Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations
    ⭐code
  • Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring
    ⭐code
  • [NewsNet: A Novel Benchmark for Hierarchical Temporal Segmentation]视频理解(论文未公开)
• 视频分类
  • Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting
    ⭐code
• 视频描述
  • Fine-grained Audible Video Description
• 视频摘要
  • Align and Attend: Multimodal Summarization with Dual Contrastive Losses
    ⭐code
• 视频识别
  • Frame Flexible Network
    ⭐code
  • Use Your Head: Improving Long-Tail Video Recognition
• Video Deflickering(去闪烁)
  • Blind Video Deflickering by Neural Filtering with a Flawed Atlas
    ⭐code
• 时间句子定位(TSG)
  • You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos
• VAD
  • Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection
  • Video Event Restoration Based on Keyframes for Video Anomaly Detection

• Improving GAN Training via Feature Space Shrinkage
  ⭐code
• CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing
• NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs
  ⭐code
• Graph Transformer GANs for Graph-Constrained House Generation
• Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models
  ⭐code
• Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesis
  ⭐code
• VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs
  ⭐code
• Discriminator-Cooperated Feature Map Distillation for GAN Compression
  ⭐code
• Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field
  ⭐code
• 图像-文本合成
  • Scaling up GANs for Text-to-Image Synthesis
    🏠project

• DSI2I: Dense Style for Unpaired Image-to-Image Translation
• Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
  ⭐code
• 3D-Aware Multi-Class Image-to-Image Translation with NeRFs
• 图像翻译
  • Masked and Adaptive Transformer for Exemplar Based Image Translation
    ⭐code

• Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition
• Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition
  👍CVPR 2023 | 人脸识别路漫漫：清华、北大等提出AT3D人脸识别系统攻击方法
• DiffusionRig: Learning Personalized Priors for Facial Appearance Editing
  ⭐code
• [Probabilistic Knowledge Distillation of Face Ensembles]人脸(论文未公开)
• DCFace: Synthetic Face Generation with Dual Condition Diffusion Model
  ⭐code
• 3D 人脸
  • Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images
  • Learning a 3D Morphable Face Reflectance Model from Low-cost Data
    🏠project
  • NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images
    ⭐code
  • FaceLit: Neural 3D Relightable Faces
  • [Learning Neural Proto-face Field for Disentangled 3D Face Modeling In the Wild]人脸(论文未公开)
• 人脸重建
  • A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images
    🏠project
• 人脸恢复
  • DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration
• 人脸匿名化
  • Attribute-preserving Face Dataset Anonymization via Latent Code Optimization
    ⭐code
• 裸眼年龄识别
  • DAA: A Delta Age AdaIN operation for age estimation via binary code transformer
• 情绪识别
  • Context De-confounded Emotion Recognition
  • Decoupled Multimodal Distilling for Emotion Recognition
    ⭐code
• 人像照明
  • LightPainter: Interactive Portrait Relighting with Freehand Scribble
• 人脸活体检测
  • Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment
  • Instance-Aware Domain Generalization for Face Anti-Spoofing
    ⭐code
  • [Instance-Aware Domain Generalization for Face Anti-Spoofing]人脸(论文未公开)
• 说话头
  • OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering
    ⭐code
  • Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert
  • [High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning]说话人脸生成(论文未公开)
  • GANHead: Towards Generative Animatable Neural Head Avatars
    ⭐code
  • One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field
    🏠project
• 人脸分割
  • Parameter Efficient Local Implicit Image Function Network for Face Segmentation
• 眨眼检测
  • Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video
• 三维头像生成
  • Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videos
    ⭐code
  • OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis
  • PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360◦
• 人脸表情识别
  • [Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition]人脸(论文未公开)
• 微表情识别
  • Micron-BERT: BERT-based Facial Micro-Expression Recognition
    ⭐code微表情识别

• PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision
  🏠project
• Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning
  ⭐code
• Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching
  ⭐code
• SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field
  ⭐code
• 3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process
  ⭐code
• 3D Concept Learning and Reasoning from Multi-View Images
  🏠project
• PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\circ}$
  ⭐code
• Persistent Nature: A Generative Model of Unbounded 3D Worlds
  🏠project
• TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision
• Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylization
• On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks
  ⭐code
• SUDS: Scalable Urban Dynamic Scenes
  🏠project
• Understanding and Improving Features Learned in Deep Functional Maps
  ⭐code
• TMO: Textured Mesh Acquisition of Objects with a Mobile Device by using Differentiable Rendering
  ⭐code
• Generalizable Local Feature Pre-training for Deformable Shape Analysis
  ⭐code
• CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
  🏠project
• CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes
  🏠project
• HOLODIFFUSION: Training a 3D Diffusion Model using 2D Images
  ⭐code
• Multi-View Azimuth Stereo via Tangent Space Consistency
  ⭐code
• 3D Line Mapping Revisited
  ⭐code
• NeRF-Supervised Deep Stereo
  ⭐code
  ⭐code
• Robust Outlier Rejection for 3D Registration with Variational Bayes三维
• Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation
• 三维重建
  • Neural Lens Modeling
    ⭐code
  • ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency
    🏠project
  • BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
    ⭐code
  • PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters
    ⭐code
  • Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly
  • MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices
    🏠project
  • Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container
    ⭐code
  • SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates
    ⭐code
  • MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision
    🏠project
  • Scalable, Detailed and Mask-Free Universal Photometric Stereo
    ⭐code
  • NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction
  • Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction
  • NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images
    🏠project
• 深度估计
  • Fully Self-Supervised Depth Estimation from Defocus Clue
    ⭐code
  • iDisc: Internal Discretization for Monocular Depth Estimation
    🏠project
  • HRDFuse: Monocular 360°Depth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributions
    🏠project
  • DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium
    ⭐code
    ⭐code
  • Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation
    ⭐code
    👍CVPR2023 | 轻量高效的自监督深度估计框架Lite-Mono
• 室内场景重建
  • I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs
    🏠project
• 场景重建
  • Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes
    ⭐code

• 手势
  • A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image
    ⭐code3D交互手势姿势估计
  • 音频驱动的联合语音手势生成
    • Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation
      ⭐code
  • 3D手势合成
    • Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglement
  • 手部重建
    • ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
      ⭐code
    • MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction
    • POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo
      ⭐code
  • 3D手部恢复
    • Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild
      ⭐code
    • Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding
      ⭐code
• 人体
  • HPE
    • DistilPose: Tokenized Pose Regression with Heatmap Distillation
    • PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation
      ⭐code
    • Human Pose as Compositional Tokens
      ⭐code
    • Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video
    • Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation
    • Human Pose Estimation in Extremely Low-Light Conditions
  • 3D HPE
    • PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers
    • PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation
      ⭐code
      ⭐code
    • 3D Human Pose Estimation via Intuitive Physics
      🏠project
  • 4D HPE
    • SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments
      ⭐code
  • 网格恢复
    • POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery
      ⭐code
    • One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
      ⭐code
      👍CVPR2023 IDEA与清华提出首个一阶段3D全身人体网格重建算法OSX
  • 三维人体网格估计
    • 3D Human Mesh Estimation from Virtual Markers
      ⭐code
  • 3D人体重建
    • High-fidelity 3D Human Digitization from Single 2K Resolution Images
      ⭐code
    • FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER
      🏠project
• 多人姿态预测
  • Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting
    ⭐code
• 人体解析
  • Semantic Human Parsing via Scalable Semantic Transfer over Multiple Label Domains
    ⭐code

• Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features
• Learning Action Changes by Measuring Verb-Adverb Textual Relationships
  ⭐code
• STMixer: A One-Stage Sparse Action Detector
• AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation
• On the Benefits of 3D Pose and Tracking for Human Action Recognition
  ⭐code
• 基于骨架的动作识别
  • Learning Discriminative Representations for Skeleton Based Action Recognition
  • Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition
    🏠project
  • 3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition
  • HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
    ⭐code
• 基于关键点的动作识别
  • Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling
• 时序动作识别
  • TriDet: Temporal Action Detection with Relative Boundary Modeling
    ⭐code
  • Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection
• 开集动作识别
  • Open Set Action Recognition via Multi-Label Evidential Learning
  • Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition
    ⭐code
• 基于MoCap的动作识别
  • STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition
    ⭐code
• 小样本动作识别
  • MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition
    ⭐code
• 半监督动作识别
  • TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
    ⭐code

• Neural Intrinsic Embedding for Non-rigid Point Cloud Matching
• SCPNet: Semantic Scene Completion on Point Cloud
• Rotation-Invariant Transformer for Point Cloud Matching
• Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants with no False Negatives and no False Positives
  🏠project
• VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud
  ⭐code
• Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priors
  ⭐code
• Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis
• Spatiotemporal Self-supervised Learning for Point Clouds in the Wild
  ⭐code
• NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud
  ⭐code
• IterativePFN: True Iterative Point Cloud Filtering
  ⭐code
• 3D点云
  • Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
    ⭐code
  • NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolation
    ⭐code
    ⭐code
  • Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation
    ⭐code
• 点云实例分割
  • ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
• 点云分类
  • PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees
• 点云补全
  • ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer
    ⭐code
  • ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion
    ⭐code
• 点云配准
  • Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration
    ⭐code
  • Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration
  • Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
    ⭐code
• 点云理解
  • Self-positioning Point-based Transformer for Point Cloud Understanding
    ⭐code
• 点云重建
  • Learning to Measure the Point Cloud Reconstruction Loss in a Representation Space

• Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking
  ⭐code
• Joint Visual Grounding and Tracking with Natural Language Specification
  ⭐code
• Generalized Relation Modeling for Transformer Tracking
  ⭐code
• DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks
  ⭐code
• 多目标跟踪
  • Referring Multi-Object Tracking
    ⭐code
  • MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking
• 细胞跟踪
  • Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses
    ⭐code
• 多模态跟踪
  • Visual Prompt Multi-Modal Tracking
    ⭐code

• Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR
  ⭐code
• DynamicDet: A Unified Dynamic Architecture for Object Detection
  ⭐code
• ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
  ⭐code
• Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection
  ⭐code
• DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment
• Curricular Object Manipulation in LiDAR-based Object Detection
  ⭐code
• Detecting Everything in the Open World: Towards Universal Object Detection
  ⭐code
  👍CVPR 2023 | 标注500类，检测7000类！清华大学等提出通用目标检测算法UniDetector
• STDLens: Model Hijacking-resilient Federated Learning for Object Detection
  ⭐code
• What Can Human Sketches Do for Object Detection?
  ⭐code
• CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
• Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects
  ⭐code
• Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection
  ⭐code
• Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection
• T-SEA: Transfer-based Self-Ensemble Attack on Object Detection
  ⭐code
  👍CVPR 2023 | 北大提出T-SEA: 自集成策略实现更强的黑盒攻击迁移性
• Knowledge Combination to Learn Rotated Detection Without Rotated Annotation
• Learning to Name Classes for Vision and Language Models
• Universal Instance Perception as Object Discovery and Retrieval
  ⭐code
• Continual Detection Transformer for Incremental Object Detection目标检测
• Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains
  ⭐code目标检测
• 目标定位
  • LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding
    🏠project
  • Egocentric Audio-Visual Object Localization
• Open-World检测
  • CapDet: Unifying Dense Captioning and Open-World Detection Pretraining
• 3D OD
  • Virtual Sparse Convolution for Multimodal 3D Object Detection
    ⭐code
  • LinK: Linear Kernel for LiDAR-based 3D Perception
    ⭐code
  • 3D Video Object Detection with Learnable Object-Centric Global Optimization
    ⭐code
  • X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection
    ⭐code
  • Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving
  • Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency
    ⭐code
  • Viewpoint Equivariance for Multi-View 3D Object Detection
    ⭐code
  • Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving
    ⭐code
  • Collaboration Helps Camera Overtake LiDAR in 3D Detection
    ⭐code
    ⭐code
  • OcTr: Octree-based Transformer for 3D Object Detection
  • MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequences
    ⭐code
  • MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer
  • MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
    ⭐code
  • NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations
  • VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
    ⭐code
  • Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection
    ⭐code
  • LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion
    ⭐code
  • PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection
    ⭐code
  • CAPE: Camera View Position Embedding for Multi-View 3D Object Detection
    ⭐code
  • Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection
    ⭐code
  • Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection
    ⭐code3D目标检测
• 端到端目标检测
  • Dense Distinct Query for End-to-End Object Detection
    ⭐code
• 半监督目标检测
  • Active Teacher for Semi-Supervised Object Detection
    ⭐code
  • SOOD: Towards Semi-Supervised Oriented Object Detection
    ⭐code
  • MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection
    ⭐code
• 弱监督目标检测
  • DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection
• 小样本目标检测
  • NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging
  • Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection
  • DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection
    ⭐code
• 域适应目标检测
  • 2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection
• 显著目标检测
  • Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings
• 红外目标检测
  • Physically Adversarial Infrared Patches with Learnable Shapes and Locations
• 伪装目标检测
  • Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers
    ⭐code
    ⭐code
• 密集目标检测
  • Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
    ⭐code
• 目标发现
  • Object Discovery from Motion-Guided Tokens
• 小目标检测
  • 红外小目标检测
    • Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision
      ⭐code

• 视频字幕
  • Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
    🏠project
  • Text with Knowledge Graph Augmented Transformer for Video Captioning
  • Positive-Augmented Constrastive Learning for Image and Video Captioning Evaluation
    ⭐code
• 图像字幕
  • Cross-Domain Image Captioning with Discriminative Finetuning
  • Model-Agnostic Gender Debiased Image Captioning
  • A-CAP: Anticipation Captioning with Commonsense Knowledge字幕

• Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models
  ⭐code
• Tunable Convolutions with Parametric Multi-Loss Optimization
• 阴影去除
  • ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
  • DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering
• 图像恢复
  • Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
    ⭐code
  • Burstormer: Burst Image Restoration and Enhancement Transformer
  • Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display Camera
    ⭐code
  • Generative Diffusion Prior for Unified Image Restoration and Enhancement
  • Bitstream-Corrupted JPEG Images are Restorable: Two-stage Compensation and Alignment Framework for Image Restoration
    ⭐code
• 图像质量评估
  • Quality-aware Pre-trained Models for Blind Image Quality Assessment
  • Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
    ⭐code
  • An Image Quality Assessment Dataset for Portraits
    ⭐code
  • Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild
• 去雾
  • Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior
    ⭐code
  • Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
  • RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors
• 去雨
  • Learning A Sparse Transformer Network for Effective Image Deraining
    ⭐code
• 去噪
  • Masked Image Training for Generalizable Deep Image Denoising
  • Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising
    ⭐code
  • Real-time Controllable Denoising for Image and Video
  • LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising
    ⭐code
  • Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations
  • Learning with Noisy labels via Self-supervised Adversarial Noisy Masking去噪
  • Learning from Noisy Labels with Decoupled Meta Label Purifier去噪
• 去模糊
  • HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering
    ⭐code
  • $\text{DC}^2$: Dual-Camera Defocus Control by Learning to Refocus
    ⭐code去模糊
  • HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering
    ⭐code
• 去鬼影
  • A Unified HDR Imaging Method with Pixel and Patch Level
  • SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders
• 去反射光斑
  • Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
    ⭐code
• 图像缩放
  • HyperThumbnail: Real-time 6K Image Rescaling with Rate-distortion Optimization
    ⭐code
• 瞬间恢复与增强
  • Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement
• 图像增强
  • Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement

• Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervisio
• MP-Former: Mask-Piloted Transformer for Image Segmentation
  ⭐code
• Explicit Visual Prompting for Low-Level Structure Segmentations
  ⭐code
• Focused and Collaborative Feedback Integration for Interactive Image Segmentation
  ⭐code
• FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation
  🏠project
  在 VIS、VOS、MOTS 三个下游视频分割任务的五个数据集上，将 InstMove 插入到现有 SOTA 模型可以进一步带来 1~5 个点的提升。
• Zero-shot Referring Image Segmentation with Global-Local Context Features
  ⭐code
• Meta Compositional Referring Expression Segmentation
• MED-VT: Multiscale Encoder-Decoder Video Transformer with Application to Object Segmentation分割
• 3D分割
  • EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision
    🏠project
• 全景分割
  • You Only Segment Once: Towards Real-Time Panoptic Segmentation
    ⭐code
• 实例分割
  • DynaMask: Dynamic Mask Selection for Instance Segmentation
    ⭐code
  • DoNet: Deep De-overlapping Network for Cytology Instance Segmentation
    ⭐code
  • FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation
    ⭐code
  • SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentation
    ⭐code
  • Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations
    ⭐code
  • 弱监督实例分割
    • The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation
      ⭐code
• 语义分割
  • IFSeg: Image-free Semantic Segmentation via Vision-Language Model
    ⭐code
  • Continual Semantic Segmentation with Automatic Memory Sample Selection
  • Federated Incremental Semantic Segmentation
    ⭐code
  • Delivering Arbitrary-Modal Semantic Segmentation
    ⭐code
  • Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation
  • [A Simple Framework for Text-Supervised Semantic Segmentation]
    ⭐code论文未公开
    在 PASCAL VOC 2012、PASCAL Context 和 COCO 数据集上的表现明显优于之前最先进的方法。
  • Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors
  • Generative Semantic Segmentation
    ⭐code
  • Reliability in Semantic Segmentation: Are We on the Right Track?
    ⭐code
  • Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation
  • Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation
    ⭐code
  • Instant Domain Augmentation for LiDAR Semantic Segmentation
    🏠project
  • Leveraging Hidden Positives for Unsupervised Semantic Segmentation
    ⭐code
  • 域适应语义分割
    • DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic Segmentation
      ⭐code
  • 半监督语义分割
    • Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation
      ⭐code
  • 弱监督语义分割
    • Token Contrast for Weakly-Supervised Semantic Segmentation
      ⭐code
  • 点云语义分割
    • Novel Class Discovery for 3D Point Cloud Semantic Segmentation
      ⭐code
  • 3D 语义分割
    • Seg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving
      ⭐code
    • 3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds
      ⭐code
• 交互式分割
  • Interactive Segmentation as Gaussian Process Classification
    ⭐code
• 小样本分割
  • Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
    ⭐code
• VSS
  • Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos
    ⭐code
  • Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation
    ⭐code
• VOS
  • InstMove: Instance Motion for Object-centric Video Segmentation
    ⭐code
  • MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation
  • Boosting Video Object Segmentation via Space-time Correspondence Learning
    ⭐code
  • Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation
    ⭐code
  • Two-shot Video Object Segmentation
    ⭐code
• VIS
  • Mask-Free Video Instance Segmentation
    ⭐code
    🏠project
    ⭐code
• 场景理解
  • FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
  • Language-driven Open-Vocabulary 3D Scene Understanding
    ⭐code
    🏠project
• 抠图
  • Adaptive Human Matting for Dynamic Videos
    ⭐code

• Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation
• Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning
• Noisy Correspondence Learning with Meta Similarity Correction
• Efficient Multimodal Fusion via Interactive Prompting
• Representing Volumetric Videos as Dynamic MLP Maps
  ⭐code
• Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation
• Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness
• DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks
• EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization
• Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models
• A Meta-Learning Approach to Predicting Performance and Data Requirements
• Multimodal Prompting with Missing Modalities for Visual Recognition
  ⭐code
• Masked Images Are Counterfactual Samples for Robust Fine-tuning
• UniHCP: A Unified Model for Human-Centric Perceptions
  ⭐code
• DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network
  ⭐code
• Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization
• Progressive Open Space Expansion for Open-Set Model Attribution
  ⭐code
• TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets
  ⭐code
• HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
  ⭐code
• 3D Cinemagraphy from a Single Image
  🏠project
• Masked Image Modeling with Local Multi-Scale Reconstruction
  ⭐code
• Revisiting Rotation Averaging: Uncertainties and Robust Losses
  ⭐code
• Unifying Layout Generation with a Decoupled Diffusion Model
• Adversarial Counterfactual Visual Explanations
  ⭐code
• Trainable Projected Gradient Method for Robust Fine-tuning
  ⭐code
• Partial Network Cloning
  ⭐code
• Extracting Class Activation Maps from Non-Discriminative Features as well
  ⭐code
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization
  ⭐code
• Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
  ⭐code
• Visibility Constrained Wide-band Illumination Spectrum Design for Seeing-in-the-Dark
  ⭐code
• PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignment
  ⭐code
• Boundary Unlearning
  🏠project
• ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals
• VecFontSDF: Learning to Reconstruct and Synthesize High-quality Vector Fonts via Signed Distance Functions
• BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
• Learning a Depth Covariance Function
  ⭐code
• A Bag-of-Prototypes Representation for Dataset-Level Applications
• CrOC: Cross-View Online Clustering for Dense Visual Representation Learning
  ⭐code
• Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels
  ⭐code
• Marching-Primitives: Shape Abstraction from Signed Distance Function
  ⭐code
• Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization
• SIEDOB: Semantic Image Editing by Disentangling Object and Background
• Robust Test-Time Adaptation in Dynamic Scenarios
  ⭐code
• Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck
  ⭐code
• IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients
• Compacting Binary Neural Networks by Sparse Kernel Selection
• PDPP:Projected Diffusion for Procedure Planning in Instructional Videos
  ⭐code
• Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph
  ⭐code
• Quantum Multi-Model Fitting
  ⭐code
• Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation
• Adaptive Spot-Guided Transformer for Consistent Local Feature Matching
  ⭐code
  ⭐code
• PMatch: Paired Masked Image Modeling for Dense Geometric Matching
  ⭐code
• ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing
  ⭐code
• Single Image Depth Prediction Made Better: A Multivariate Gaussian Take
• Why is the winner the best?
• Disorder-invariant Implicit Neural Representation
  ⭐code
• HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
  ⭐code
• Enhancing Deformable Local Features by Jointly Learning to Detect and Describe Keypoints
  🏠project
• SMPConv: Self-moving Point Representations for Continuous Convolution
  ⭐code
• VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution
  ⭐code
• Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling
• [Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce]论文未公开
• [Meta Compositional Referring Expression Segmentation]论文未公开
• Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce多模态预训练
• Adaptive Assignment for Geometry Aware Local Feature Matching
  ⭐code特征匹配
• Hard Patches Mining for Masked Image Modeling