ICCV 2025 论文和开源项目合集(Papers with Code)

ICCV 2025 Accepance Rate of 24% = 2699 / 11239

注1：欢迎各位大佬提交issue，分享ICCV 2025论文和开源项目！

注2：关于往年CV顶会论文以及其他优质CV论文和大盘点，详见： https://github.com/amusi/daily-paper-computer-vision

• CVPR 2025
• ECCV 2024

欢迎扫码加入【CVer学术交流群】，可以获取ICCV 2025等最前沿工作！这是最大的计算机视觉AI知识星球！每日更新，第一时间分享最新最前沿的计算机视觉、AIGC、扩散模型、多模态、深度学习、自动驾驶、医疗影像和遥感等方向的学习资料，快加入学起来！

【ICCV 2025 论文和开源代码目录】

• 3DGS(Gaussian Splatting)
• Agent)
• Avatars
• Backbone
• CLIP
• Mamba
• Embodied AI
• GAN
• GNN
• 多模态大语言模型(MLLM)
• 大语言模型(LLM)
• 世界模型(World Model)
• OCR
• NeRF
• DETR
• 扩散模型(Diffusion Models)
• ReID(重识别)
• 长尾分布(Long-Tail)
• Vision Transformer
• 视觉和语言(Vision-Language)
• 自监督学习(Self-supervised Learning)
• 数据增强(Data Augmentation)
• 目标检测(Object Detection)
• 异常检测(Anomaly Detection)
• 目标跟踪(Visual Tracking)
• 语义分割(Semantic Segmentation)
• 实例分割(Instance Segmentation)
• 全景分割(Panoptic Segmentation)
• 医学图像(Medical Image)
• 医学图像分割(Medical Image Segmentation)
• 视频目标分割(Video Object Segmentation)
• 视频实例分割(Video Instance Segmentation)
• 参考图像分割(Referring Image Segmentation)
• 图像抠图(Image Matting)
• 图像编辑(Image Editing)
• Low-level Vision
• 超分辨率(Super-Resolution)
• 去噪(Denoising)
• 去模糊(Deblur)
• 自动驾驶(Autonomous Driving)
• 3D点云(3D Point Cloud)
• 3D目标检测(3D Object Detection)
• 3D语义分割(3D Semantic Segmentation)
• 3D目标跟踪(3D Object Tracking)
• 3D语义场景补全(3D Semantic Scene Completion)
• 3D配准(3D Registration)
• 3D人体姿态估计(3D Human Pose Estimation)
• 3D人体Mesh估计(3D Human Mesh Estimation)
• 3D Visual Grounding(3D视觉定位)
• 医学图像(Medical Image)
• 图像生成(Image Generation)
• 视频生成(Video Generation)
• 3D生成(3D Generation)
• 视频理解(Video Understanding)
• 行为检测(Action Detection)
• 具身智能(Embodied AI)
• 文本检测(Text Detection)
• 知识蒸馏(Knowledge Distillation)
• 模型剪枝(Model Pruning)
• 图像压缩(Image Compression)
• 三维重建(3D Reconstruction)
• 深度估计(Depth Estimation)
• 轨迹预测(Trajectory Prediction)
• 车道线检测(Lane Detection)
• 图像描述(Image Captioning)
• 视觉问答(Visual Question Answering)
• 手语识别(Sign Language Recognition)
• 视频预测(Video Prediction)
• 新视点合成(Novel View Synthesis)
• Zero-Shot Learning(零样本学习)
• 立体匹配(Stereo Matching)
• 特征匹配(Feature Matching)
• 暗光图像增强(Low-light Image Enhancement)
• 场景图生成(Scene Graph Generation)
• 风格迁移(Style Transfer)
• 隐式神经表示(Implicit Neural Representations)
• 图像质量评价(Image Quality Assessment)
• 视频质量评价(Video Quality Assessment)
• 压缩感知(Compressive Sensing)
• 数据集(Datasets)
• 新任务(New Tasks)
• 其他(Others)

3DGS(Gaussian Splatting)

Agent

Avatars

Backbone

TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba

• Paper: https://arxiv.org/abs/2411.17473
• Code: https://github.com/xwmaxwma/TinyViM

CLIP

Mamba

TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba

• Paper: https://arxiv.org/abs/2411.17473
• Code: https://github.com/xwmaxwma/TinyViM

Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers

• Project：https://tiger-ai-lab.github.io/Vamba/
• Paper：https://arxiv.org/abs/2503.11579
• Code：https://github.com/TIGER-AI-Lab/Vamba

Embodied AI

GAN

OCR

NeRF

DETR

Prompt

多模态大语言模型(MLLM)

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers

• Paper: https://arxiv.org/abs/2501.16297
• Code: https://github.com/JiuTian-VL/JiuTian-FALCON
• Project: https://jiutian-vl.github.io/FALCON.github.io/

大语言模型(LLM)

World Model(世界模型)

Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning

• Project: https://yijun-yang.github.io/MeWM/
• Paper: https://arxiv.org/abs/2506.02327
• Code: https://github.com/scott-yjyang/MeWM

ReID(重识别)

扩散模型(Diffusion Models)

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

• Paper: https://arxiv.org/abs/2503.06923
• Code: https://github.com/Shenyi-Z/TaylorSeer

Vision Transformer

视觉和语言(Vision-Language)

目标检测(Object Detection)

异常检测(Anomaly Detection)

目标跟踪(Object Tracking)

医学图像(Medical Image)

Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning

• Project: https://yijun-yang.github.io/MeWM/
• Paper: https://arxiv.org/abs/2506.02327
• Code: https://github.com/scott-yjyang/MeWM

医学图像分割(Medical Image Segmentation)

自动驾驶(Autonomous Driving)

Where, What, Why: Towards Explainable Driver Attention Prediction

• Paper: https://arxiv.org/abs/2506.23088
• Code: https://github.com/yuchen2199/Explainable-Driver-Attention-Prediction
• Project: https://github.com/yuchen2199/Explainable-Driver-Attention-Prediction

ROADWork Dataset: Learning to Recognize, Observe, Analyze and Drive Through Work Zones

• Paper: https://arxiv.org/abs/2406.07661
• Code: https://github.com/anuragxel/roadwork-dataset
• Project: https://www.cs.cmu.edu/~ILIM/roadwork_dataset/

DriveMM: All-in-One Large Multimodal Model for Autonomous Driving

• Project: https://zhijian11.github.io/DriveMM/
• Paper: https://arxiv.org/abs/2412.07689
• Code: https://github.com/zhijian11/DriveMM

3D点云(3D-Point-Cloud)

3D目标检测(3D Object Detection)

3D语义分割(3D Semantic Segmentation)

Low-level Vision

EAMamba: Efficient All-Around Vision State Space Model for Image Restoration

• Paper: https://arxiv.org/abs/2506.22246
• Code: https://github.com/daidaijr/EAMamba

超分辨率(Super-Resolution)

去噪(Denoising)

图像去噪(Image Denoising)

3D人体姿态估计(3D Human Pose Estimation)

#3D Visual Grounding(3D视觉定位)

图像生成(Image Generation)

DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models

• Paper: https://github.com/limuloo/DreamRenderer
• Code: https://arxiv.org/abs/2503.12885

视频生成(Video Generation)

图像编辑(Image Editing)

Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing

• Project: https://eff-edit.github.io
• Paper: https://arxiv.org/abs/2503.10270
• Code: https://github.com/yuriYanZeXuan/EEdit

视频编辑(Video Editing)

3D生成(3D Generation)

3D重建(3D Reconstruction)

人体运动生成(Human Motion Generation)

视频理解(Video Understanding)

Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers

• Project：https://tiger-ai-lab.github.io/Vamba/
• Paper：https://arxiv.org/abs/2503.11579
• Code：https://github.com/TIGER-AI-Lab/Vamba

具身智能(Embodied AI)

知识蒸馏(Knowledge Distillation)

深度估计(Depth Estimation)

立体匹配(Stereo Matching)

暗光图像增强(Low-light Image Enhancement)

图像压缩(Image Compression)](#IC)

场景图生成(Scene Graph Generation)

风格迁移(Style Transfer)

图像质量评价(Image Quality Assessment)

视频质量评价(Video Quality Assessment)

压缩感知(Compressive Sensing)

数据集(Datasets)

ROADWork Dataset: Learning to Recognize, Observe, Analyze and Drive Through Work Zones

• Paper: https://arxiv.org/abs/2406.07661
• Code: https://github.com/anuragxel/roadwork-dataset
• Project: https://www.cs.cmu.edu/~ILIM/roadwork_dataset/

其他(Others)

Music Grounding by Short Video

• Project: https://rucmm.github.io/VMMR/
• Paper: https://arxiv.org/abs/2408.16990
• Code link: https://github.com/xxayt/MGSV