Awesome

WACV-2025-Papers

会议时间：2025年2月28日–3月4日

会议网址：https://wacv2025.thecvf.com/

❣❣❣ WACV 2024 论文分类整理ing

查看2024年综述文献点这里↘️2024-CV-Surveys

2025 年论文分类汇总戳这里

↘️WACV-2025-Papers ↘️CVPR-2025-Papers

2024 年论文分类汇总戳这里

↘️WACV-2024-Papers ↘️CVPR-2024-Papers ↘️ECCV-2024-Papers

2023 年论文分类汇总戳这里

2022 年论文分类汇总戳这里

2021 年论文分类汇总戳这里

2020 年论文分类汇总戳这里

12月13日更新 2 篇，共计 155+2 篇。

• SyncViolinist: Music-Oriented Violin Motion Generation Based on Bowing and Fingering<br>:star:code
• Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering

<br>:star:[code] <br>:house:[project] ASDF

Transformer

• LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones

Dense Prediction(密集预测)

• Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization<br>:star:code

Neural Radiance Fields

• GANESH: Generalizable NeRF for Lensless Imaging<br>:star:code

Anomaly Detection(异常检测)

• SPACE: SPAtial-aware Consistency rEgularization for anomaly detection in Industrial applications
• Adaptive Deviation Learning for Visual Anomaly Detection with Data Contamination
• Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera
• ROADS: Robust Prompt-driven Multi-Class Anomaly Detection under Domain Shift
• FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data<br>:star:code
• 异常定位
  • Towards Zero-shot 3D Anomaly Localization

Deepfake

• DeCLIP: Decoding CLIP representations for deepfake localization<br>:star:code

Robots(机器人)

• SLAM
  • Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction<br>:star:code

Scene(场景)

• LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations<br>:star:code

Object Pose Estimation(物体姿态估计)

• Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching<br>:star:code

Dataset/Benchmark(数据集/基准)

• CT to PET Translation: A Large-scale Dataset and Domain-Knowledge-Guided Diffusion Approach<br>:star:code
• PV-VTT: A Privacy-Centric Dataset for Mission-Specific Anomaly Detection and Natural Language Interpretation
• SynDroneVision: A Synthetic Dataset for Image-Based Drone Detection
• SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark<br>:star:code<br>:star:code
• DrIFT: Autonomous Drone Dataset with Integrated Real and Synthetic Data, Flexible Views, and Transformed Domains<br>:star:code
• 基准
  • GazeSearch: Radiology Findings Search Benchmark
  • ARTeFACT: Benchmarking Segmentation Models on Diverse Analogue Media Damage<br>:star:code

虚拟头像

• Gaussian Déjà-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities

Vision-Language

• Active Learning for Vision-Language Models
• @Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology<br>:star:code<br>:house:project
• Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models
• Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis
• Retaining and Enhancing Pre-trained Knowledge in Vision-Language Models with Prompt Ensembling
• 视频语言
  • ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos
• VLN
  • To Ask or Not to Ask? Detecting Absence of Information in Vision and Language Navigation
  • Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks
• Visual Grounding
  • Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding

Semi/self-supervised learning(半/自监督)

• 自监督
  • HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms
  • Self-Supervised Learning with Probabilistic Density Labeling for Rainfall Probability Estimation<br>:star:code

Few/Zero-Shot Learning/DG/A(小/零样本/域泛化/域适应)

• 域适应
  • AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation

Machine Learning(机器学习)

• 类增量
  • Covariance-based Space Regularization for Few-shot Class Incremental Learning
• 对比学习
  • MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning
• 持续学习
  • Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation<br>:star:code
  • Memory-efficient Continual Learning with Neural Collapse Contrastive
  • Exploring the Stability Gap in Continual Learning: The Role of the Classification Head
• 多任务学习
  • Diffusion-based Visual Anagram as Multi-task Learning<br>:star:code

Motion Generation(人体运动生成)

• SyncViolinist: Music-Oriented Violin Motion Generation Based on Bowing and Fingering<br>:star:code

GAN/Image Synthesis(图像生成)

• 纹理生成
  • Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds
• 图像生成
  • RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation(https://github.com/SonyResearch/RAW-Diffusion)
  • MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning<br>:star:code<br>:house:project
• 食谱生成
  • Retrieval Augmented Recipe Generation
• 图像编辑
  • Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing<br>:star:code
• 文本-图像
  • DreamBlend: Advancing Personalized Fine-tuning of Text-to-Image Diffusion Models
• 图像-图像翻译
  • Uncertainty-Aware Regularization for Image-to-Image Translation

Visual Question Answering(视觉问答)

• Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering

OCR

• Text Change Detection in Multilingual Documents Using Image Comparison

3D(三维重建\三维视觉)

• Planar Gaussian Splatting
• LIPIDS: Learning-based Illumination Planning In Discretized (Light) Space for Photometric Stereo
• 深度估计
  • GET-UP: GEomeTric-aware Depth Estimation with Radar Points UPsampling
  • Revisiting Disparity from Dual-Pixel Images: Physics-Informed Lightweight Depth Estimation
  • MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications<br>:star:code

Point Cloud(点云)

• PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing<br>:star:code
• 3D 点云
  • Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models<br>:star:code
• 点云分类
  • Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification
• 点云分割
  • ZAHA: Introducing the Level of Facade Generalization and the Large-Scale Point Cloud Facade Semantic Segmentation Benchmark Dataset
• 点云配准
  • XR-MBT: Multi-modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration

Person Re-id

• ReMix: Training Generalized Person Re-identification on a Mixture of Data
• AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy<br>:star:code
• 换衣重识别
  • DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID<br>:star:code
• 行人搜索
  • Swap Path Network for Robust Person Search Pre-training<br>:star:code

Action Detection(动作检测)

• 开放词汇动作检测
  • Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection<br>:star:code
• 基于骨架的动作识别
  • Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition

Human Pose Estimation

• 人体重建
  • DiHuR: Diffusion-Guided Generalizable Human Reconstruction
• 人体网格恢复
  • Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery<br>:star:code
• 三维姿态估计
  • ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening<br>:star:code
• 人体运动恢复
  • RopeTP: Global Human Motion Recovery via Integrating Robust Pose Estimation with Diffusion Trajectory Prior
• 手势生成
  • Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audios

Medical Image Progress(医学影响处理)

• PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices<br>:star:code
• Volumetric Conditioning Module to Control Pretrained Diffusion Models for 3D Medical Images<br>:star:code
• AMNCutter: Affinity-Attention-Guided Multi-View Normalized Cutter for Unsupervised Surgical Instrument Segmentation<br>:star:code
• Multimodal Fusion Learning with Dual Attention for Medical Imaging<br>:star:code
• LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Image<br>:star:code
• 医学图像分割
  • Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanisms<br>:star:code
  • MulModSeg: Enhancing Unpaired Multi-Modal Medical Image Segmentation with Modality-Conditioned Text Embedding and Alternating Training<br>:star:code
• 医学放射科报告生成
  • ORID: Organ-Regional Information Driven Framework for Radiology Report Generation
• MRI
  • Continuous Spatio-Temporal Memory Networks for 4D Cardiac Cine MRI Segmentation
  • DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers Using MRI and PET

Autonomous Driving(自动驾驶)

• CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving<br>:house:project
• S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving
• 轨迹预测
  • Socially-Informed Reconstruction for Pedestrian Trajectory Forecasting

Biomedical(生物特征识别)

• 虹膜检测
  • A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack Detection

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

• PGRID: Power Grid Reconstruction in Informal Developments Using High-Resolution Aerial Imagery
• Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery<br>:star:code

Object Tracking(目标跟踪)

• MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation<br>:star:code
• Improving Accuracy and Generalization for Efficient Visual Tracking
• 点跟踪
  • EgoPoints: Advancing Point Tracking for Egocentric Videos<br>:star:code

Object Detection(目标检测)

• Mixed Patch Infrared-Visible Modality Agnostic Object Detection<br>:star:code<br>:house:project
• No Annotations for Object Detection in Art through Stable Diffusion<br>:star:code
• 3D OD
  • VADet: Multi-frame LiDAR 3D Object Detection using Variable Aggregation
• VOD
  • Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection

Image/Video Retrieval(图像/视频检索)

• 图像检索
  • Composed Image Retrieval for Training-Free Domain Conversion<br>:star:code
• 视频检索
  • ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising
• 信息检索
  • Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty

Image/video Compression(图像/视频压缩)

• Efficient Progressive Image Compression with Variance-aware Masking

Image Classification(图像分类)

• Enhancing Visual Classification using Comparative Descriptors
• Class-Conditioned Transformation for Enhanced Robust Image Classification<br>:star:code

Image Progress(图像/视频处理)

• 图像恢复
  • Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration
• 图像修复
  • SEM-Net: Efficient Pixel Modelling for image inpainting with Spatially Enhanced SSM<br>:star:code
  • I Dream My Painting: Connecting MLLMs and Diffusion Models via Prompt Generation for Text-Guided Multi-Mask Inpainting<br>:star:code
• 图像增强
  • Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement
• 图像质量评估
  • Dual-Representation Interaction Driven Image Quality Assessment with Restoration Assistance<br>:star:code
• 视频增强
  • UnDIVE: Generalized Underwater Video Enhancement Using Generative Priors
• 视频去模糊
  • Adaptive High-Pass Kernel Prediction for Efficient Video Deblurring<br>:star:code

Image Segmentation(图像分割)

• HSDA: High-frequency Shuffle Data Augmentation for Bird's-Eye-View Map Segmentation<br>:star:code
• 语义分割
  • COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes
  • Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-based Semantic Segmentation
  • Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation
  • Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation
  • 小样本语义分割
    • Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Images
• VSS
  • Event-guided Low-light Video Semantic Segmentation
• VPS
  • Balancing Shared and Task-Specific Representations: A Hybrid Approach to Depth-Aware Video Panoptic Segmentation<br>:house:project

Face

• Continual Learning of Personalized Generative Face Models with Experience Replay<br>:star:code
• 人脸识别
  • PETALface: Parameter Efficient Transfer Learning for Low-resolution Face Recognition<br>:house:project
• 人脸验证
  • Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification
• 人脸生成
  • Analyzing and Improving the Skin Tone Consistency and Bias in Implicit 3D Relightable Face Generators
• 人脸表情识别
  • Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation
• 人脸关键点检测
  • Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection

Othere(其它)

• Dense Depth from Event Focal Stack
• MAGMA: Manifold Regularization for MAEs<br>:star:code
• SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting
• Secrets of Edge-Informed Contrast Maximization for Event-Based Vision
• Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier<br>:star:code
• PACA: Perspective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement
• Active Event Alignment for Monocular Distance Estimation
• Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets<br>:star:code
• Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels<br>:star:code
• EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data<br>:star:code
• High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer
• SEMU-Net: A Segmentation-based Corrector for Fabrication Process Variations of Nanophotonics with Microscopic Images
• Situational Scene Graph for Structured Human-centric Situation Understanding
• Compositional Segmentation of Cardiac Images Leveraging Metadata<br>:star:code
• DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination
• TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes<br>:star:code
• MS-Glance: Non-semantic context vectors and the applications in supervising image reconstruction<br>:star:code
• Debiasify: Self-Distillation for Unsupervised Bias Mitigation
• TaxaBind: A Unified Embedding Space for Ecological Applications<br>:star:code
• Towards High-fidelity Head Blending with Chroma Keying for Industrial Applications<br>:star:code
• Through the Curved Cover: Synthesizing Cover Aberrated Scenes with Refractive Field
• HandCraft: Anatomically Correct Restoration of Malformed Hands in Diffusion Generated Images
• WAFFLE: Multimodal Floorplan Understanding in the Wild<br>:house:project
• Distillation of Diffusion Features for Semantic Correspondence<br>:star:code
• Divergent Domains, Convergent Grading: Enhancing Generalization in Diabetic Retinopathy Grading<br>:star:code
• HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning<br>:star:code
• STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing
• Design-o-meter: Towards Evaluating and Refining Graphic Designs<br>:star:code
• Ordinal Multiple-instance Learning for Ulcerative Colitis Severity Estimation with Selective Aggregated Transformer<br>:star:code
• TreeFormer: Single-view Plant Skeleton Estimation via Tree-constrained Graph Generation<br>:star:code
• I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames<br>:star:code
• Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation
• SimuScope: Realistic Endoscopic Synthetic Dataset Generation through Surgical Simulation and Diffusion Models<br>:star:code
• EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos<br>:house:project
• Multi-view Image Diffusion via Coordinate Noise and Fourier Attention
• LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization
• [SHIP: Structural Hierarchies for Instance-dependent Partial Labels]<br>本文介绍了一个模块化组件，旨在无缝集成到深度学习架构中，特别是在标签层次结构存在的情况下。SHIP增强了基于实例的部分标签学习（PLL），并在各种算法中提高了2.6%的准确率！

2020 年论文分类汇总戳这里

↘️CVPR-2020-Papers ↘️ECCV-2020-Papers

2021 年论文分类汇总戳这里

↘️ICCV-2021-Papers ↘️CVPR-2021-Papers

2022 年论文分类汇总戳这里

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

2023 年论文分类汇总戳这里

↘️CVPR-2023-Papers ↘️WACV-2023-Papers ↘️ICCV-2023-Papers ↘️2023-CV-Surveys

扫码CV君微信(注明：CVPR)入微信交流群：