ECCV 2024 论文和开源项目合集(Papers with Code)

ECCV 2024 decisions are now available！

注1：欢迎各位大佬提交issue，分享ECCV 2024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 2024
• ECCV 2022
• ECCV 2020

想看ECCV 2024和最新最全的顶会工作，欢迎扫码加入【CVer学术交流群】，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、深度学习、自动驾驶、医疗影像和AIGC等方向的学习资料，学起来！

【ECCV 2024 论文开源目录】

• 3DGS(Gaussian Splatting)
• Mamba / SSM)
• Avatars
• Backbone
• CLIP
• MAE
• Embodied AI
• GAN
• GNN
• 多模态大语言模型(MLLM)
• 大语言模型(LLM)
• NAS
• OCR
• NeRF
• DETR
• Prompt
• 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)
• 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)
• 行为识别(Action Recognition)
• 行为检测(Action Detection)
• 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)
• 场景图生成(Scene Graph Generation)
• 计数(Counting)
• 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)
• 数据集(Datasets)
• 新任务(New Tasks)
• 其他(Others)

3DGS(Gaussian Splatting)

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

• Project: https://donydchen.github.io/mvsplat
• Paper: https://arxiv.org/abs/2403.14627
• Code：https://github.com/donydchen/mvsplat

CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians

• Paper: https://arxiv.org/abs/2404.01133
• Code: https://github.com/DekuLiuTesla/CityGaussian

FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting

• Project: https://zehaozhu.github.io/FSGS/
• Paper: https://arxiv.org/abs/2312.00451
• Code: https://github.com/VITA-Group/FSGS

Mamba / SSM

VideoMamba: State Space Model for Efficient Video Understanding

• Paper: https://arxiv.org/abs/2403.06977
• Code: https://github.com/OpenGVLab/VideoMamba

ZIGMA: A DiT-style Zigzag Mamba Diffusion Model

• Paper: https://arxiv.org/abs/2403.13802
• Code: https://taohu.me/zigma/

Avatars

Backbone

CLIP

MAE

Embodied AI

GAN

OCR

Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors

• Paper: https://arxiv.org/pdf/2312.05286

• Code: https://github.com/SJTU-DeepVisionLab/FreeReal

PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer

• Paper: https://arxiv.org/abs/2407.07764
• Code: https://github.com/SJTU-DeepVisionLab/PosFormer

Occupancy

Fully Sparse 3D Occupancy Prediction

• Paper: https://arxiv.org/abs/2312.17118
• Code: https://github.com/MCG-NJU/SparseOcc

NeRF

NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields

• Project: https://nerf-mae.github.io/
• Paper: https://arxiv.org/pdf/2404.01300
• Code: https://github.com/zubair-irshad/NeRF-MAE

DETR

Prompt

多模态大语言模型(MLLM)

SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant

• Paper: https://arxiv.org/abs/2403.11299
• Code: https://github.com/heliossun/SQ-LLaVA

ControlCap: Controllable Region-level Captioning

• Paper: https://arxiv.org/abs/2401.17910
• Code: https://github.com/callsys/ControlCap

大语言模型(LLM)

NAS

ReID(重识别)

扩散模型(Diffusion Models)

ZIGMA: A DiT-style Zigzag Mamba Diffusion Model

• Paper: https://arxiv.org/abs/2403.13802
• Code: https://taohu.me/zigma/

Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation

• Paper: https://arxiv.org/abs/2403.16394
• Code: https://github.com/zdxdsw/skewed_relations_T2I

The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization

• Project: https://ut-mao.github.io/noise.github.io/
• Paper: https://arxiv.org/abs/2312.08872
• Code: https://github.com/UT-Mao/Initial-Noise-Construction

Vision Transformer

GiT: Towards Generalist Vision Transformer through Universal Language Interface

• Paper: https://arxiv.org/abs/2403.09394
• Code: https://github.com/Haiyang-W/GiT

视觉和语言(Vision-Language)

GalLoP: Learning Global and Local Prompts for Vision-Language Models

• Paper：https://arxiv.org/abs/2407.01400

目标检测(Object Detection)

Relation DETR: Exploring Explicit Position Relation Prior for Object Detection

• Paper: https://arxiv.org/abs/2407.11699v1
• Code: https://github.com/xiuqhou/Relation-DETR
• Dataset: https://huggingface.co/datasets/xiuqhou/SA-Det-100k

Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

• Project: http://yuqianfu.com/CDFSOD-benchmark/
• Paper: https://arxiv.org/pdf/2402.03094
• Code: https://github.com/lovelyqian/CDFSOD-benchmark

异常检测(Anomaly Detection)

目标跟踪(Object Tracking)

语义分割(Semantic Segmentation)

Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation

• Paper: https://arxiv.org/abs/2405.06228

• Code: https://github.com/nizhenliang/CGRSeg

医学图像(Medical Image)

Brain-ID: Learning Contrast-agnostic Anatomical Representations for Brain Imaging

• Paper: https://arxiv.org/abs/2311.16914
• Code: https://github.com/peirong26/Brain-ID

FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

• Project: https://ophai.hms.harvard.edu/datasets/harvard-fairdomain20k
• Paper : https://arxiv.org/abs/2407.08813
• Dataset: https://drive.google.com/drive/u/1/folders/1huH93JVeXMj9rK6p1OZRub868vv0UK0O
• Code: https://github.com/Harvard-Ophthalmology-AI-Lab/FairDomain

医学图像分割(Medical Image Segmentation)

ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image

• Project: https://scribbleprompt.csail.mit.edu/
• Paper: https://arxiv.org/abs/2312.07381
• Code: https://github.com/halleewong/ScribblePrompt

AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking

• Paper: https://arxiv.org/abs/2407.06468
• Code: https://github.com/ricklisz/AnatoMask

Representing Topological Self-Similarity Using Fractal Feature Maps for Accurate Segmentation of Tubular Structures

• Paper: https://arxiv.org/abs/2407.14754
• Code: https://github.com/cbmi-group/FFM-Multi-Decoder-Network

视频目标分割(Video Object Segmentation)

DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries

• Project: https://zhang-tao-whu.github.io/projects/DVIS_DAQ/
• Paper: https://arxiv.org/abs/2404.00086
• Code: https://github.com/zhang-tao-whu/DVIS_Plus

自动驾驶(Autonomous Driving)

Fully Sparse 3D Occupancy Prediction

• Paper: https://arxiv.org/abs/2312.17118
• Code: https://github.com/MCG-NJU/SparseOcc

milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing

• Paper: https://arxiv.org/abs/2306.17010
• Code: https://github.com/Toytiny/milliFlow/

4D Contrastive Superflows are Dense 3D Representation Learners

• Paper : https://arxiv.org/abs/2407.06190
• Code: https://github.com/Xiangxu-0103/SuperFlow

3D点云(3D-Point-Cloud)

3D目标检测(3D Object Detection)

3D Small Object Detection with Dynamic Spatial Pruning

• Project: https://xuxw98.github.io/DSPDet3D/
• Paper: https://arxiv.org/abs/2305.03716
• Code: https://github.com/xuxw98/DSPDet3D

Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection

• Paper: https://arxiv.org/abs/2402.03634
• Code: https://github.com/LiewFeng/RayDN

3D语义分割(3D Semantic Segmentation)

图像编辑(Image Editing)

图像补全/图像修复(Image Inpainting)

BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion

• Project https://tencentarc.github.io/BrushNet/
• Paper: https://arxiv.org/abs/2403.06976
• Code: https://github.com/TencentARC/BrushNet

视频编辑(Video Editing)

Low-level Vision

Restoring Images in Adverse Weather Conditions via Histogram Transformer

• Paper: https://arxiv.org/abs/2407.10172
• Code: https://github.com/sunshangquan/Histoformer

OneRestore: A Universal Restoration Framework for Composite Degradation

• Project https://gy65896.github.io/projects/ECCV2024_OneRestore
• Paper: https://arxiv.org/abs/2407.04621
• Code: https://github.com/gy65896/OneRestore

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)

图像生成(Image Generation)

Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models

• Paper: https://arxiv.org/abs/2404.07389
• Code: https://github.com/YasminZhang/EBAMA

Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization

• Project: https://kaminyou.com/Dense-Normalization/
• Paper: https://arxiv.org/abs/2407.04245
• Code: https://github.com/Kaminyou/Dense-Normalization

ZIGMA: A DiT-style Zigzag Mamba Diffusion Model

• Paper: https://arxiv.org/abs/2403.13802
• Code: https://taohu.me/zigma/

Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation

• Paper: https://arxiv.org/abs/2403.16394
• Code: https://github.com/zdxdsw/skewed_relations_T2I

视频生成(Video Generation)

VideoStudio: Generating Consistent-Content and Multi-Scene Videos

• Project: https://vidstudio.github.io/
• Code: https://github.com/FuchenUSTC/VideoStudio

3D生成

视频理解(Video Understanding)

VideoMamba: State Space Model for Efficient Video Understanding

• Paper: https://arxiv.org/abs/2403.06977
• Code: https://github.com/OpenGVLab/VideoMamba

C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition

• Paper: https://arxiv.org/abs/2407.06113
• Code: https://github.com/RongchangLi/ZSCAR_C2C

行为识别(Action Recognition)

SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders

• Paper: https://arxiv.org/abs/2407.13460
• Code: https://github.com/pha123661/SA-DVAE

知识蒸馏(Knowledge Distillation)

图像压缩(Image Compression)

Image Compression for Machine and Human Vision With Spatial-Frequency Adaptation

• Code: https://github.com/qingshi9974/ECCV2024-AdpatICMH
• Paper: http://arxiv.org/abs/2407.09853

立体匹配(Stereo Matching)

场景图生成(Scene Graph Generation)

计数(Counting)

Zero-shot Object Counting with Good Exemplars

• Paper: https://arxiv.org/abs/2407.04948
• Code: https://github.com/HopooLinZ/VA-Count

视频质量评价(Video Quality Assessment)

数据集(Datasets)

其他(Others)

Multi-branch Collaborative Learning Network for 3D Visual Grounding

• Paper: https://arxiv.org/abs/2407.05363v2
• Code: https://github.com/qzp2018/MCLN

PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers

• Code: https://github.com/ananthu-aniraj/pdiscoformer
• Paper: https://arxiv.org/abs/2407.04538

SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments

• Project: https://fraunhoferhhi.github.io/spvloc/
• Paper: https://arxiv.org/abs/2404.10527
• Code: https://github.com/fraunhoferhhi/spvloc

REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices

• Project: https://xdimlab.github.io/REFRAME/
• Paper: https://arxiv.org/abs/2403.16481
• Code: https://github.com/MARVELOUSJI/REFRAME