CVPR 2024 decisions are now available on OpenReview！

注1：欢迎各位大佬提交issue，分享CVPR 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 2019
• CVPR 2020
• CVPR 2021
• CVPR 2022
• CVPR 2023

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、AI绘画、图像处理、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！

• 3DGS(Gaussian Splatting)
• Avatars
• Backbone
• CLIP
• MAE
• Embodied AI
• GAN
• GNN
• 多模态大语言模型(MLLM)
• NAS
• OCR
• NeRF
• DETR
• Prompt
• Diffusion Models(扩散模型)
• 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)
• 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)
• 视频理解(Video Understanding)
• 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)
• 异常检测(Anomaly Detection)
• 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)
• 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)

Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

• Homepage: https://city-super.github.io/scaffold-gs/
• Paper: https://arxiv.org/abs/2312.00109
• Code: https://github.com/city-super/Scaffold-GS

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

• Homepage: https://shunyuanzheng.github.io/GPS-Gaussian
• Paper: https://arxiv.org/abs/2312.02155
• Code: https://github.com/ShunyuanZheng/GPS-Gaussian

GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

• Paper: https://arxiv.org/abs/2312.02134
• Code: https://github.com/huliangxiao/GaussianAvatar

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

• Paper: https://arxiv.org/abs/2311.14521
• Code: https://github.com/buaacyw/GaussianEditor

Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction

• Homepage: https://ingra14m.github.io/Deformable-Gaussians/
• Paper: https://arxiv.org/abs/2309.13101
• Code: https://github.com/ingra14m/Deformable-3D-Gaussians

SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

• Homepage: https://yihua7.github.io/SC-GS-web/
• Paper: https://arxiv.org/abs/2312.14937
• Code: https://github.com/yihua7/SC-GS

Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis

• Homepage: https://oppo-us-research.github.io/SpacetimeGaussians-website/
• Paper: https://arxiv.org/abs/2312.16812
• Code: https://github.com/oppo-us-research/SpacetimeGaussians

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

• Homepage: https://fictionarry.github.io/DNGaussian/
• Paper: https://arxiv.org/abs/2403.06912
• Code: https://github.com/Fictionarry/DNGaussian

4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

• Paper: https://arxiv.org/abs/2310.08528
• Code: https://github.com/hustvl/4DGaussians

GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models

• Paper: https://arxiv.org/abs/2310.08529
• Code: https://github.com/hustvl/GaussianDreamer

GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

• Paper: https://arxiv.org/abs/2312.02134
• Code: https://github.com/huliangxiao/GaussianAvatar

Real-Time Simulated Avatar from Head-Mounted Sensors

• Homepage: https://www.zhengyiluo.com/SimXR/
• Paper: https://arxiv.org/abs/2403.06862

RepViT: Revisiting Mobile CNN From ViT Perspective

• Paper: https://arxiv.org/abs/2307.09283
• Code: https://github.com/THU-MIG/RepViT

TransNeXt: Robust Foveal Visual Perception for Vision Transformers

• Paper: https://arxiv.org/abs/2311.17132
• Code: https://github.com/DaiShiResearch/TransNeXt

Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

• Paper: https://arxiv.org/abs/2312.03818
• Code: https://github.com/SunzeY/AlphaCLIP

EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

• Homepage: https://tai-wang.github.io/embodiedscan/
• Paper: https://arxiv.org/abs/2312.16170
• Code: https://github.com/OpenRobotLab/EmbodiedScan

MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception

• Homepage: https://iranqin.github.io/MP5.github.io/
• Paper: https://arxiv.org/abs/2312.07472
• Code: https://github.com/IranQin/MP5

LEMON: Learning 3D Human-Object Interaction Relation from 2D Images

• Paper: https://arxiv.org/abs/2312.08963
• Code: https://github.com/yyvhang/lemon_3d

An Empirical Study of Scaling Law for OCR

• Paper: https://arxiv.org/abs/2401.00028
• Code: https://github.com/large-ocr-model/large-ocr-model.github.io

ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting

• Paper: https://arxiv.org/abs/2403.00303
• Code: https://github.com/PriNing/ODM

DETRs Beat YOLOs on Real-time Object Detection

• Paper: https://arxiv.org/abs/2304.08069
• Code: https://github.com/lyuwenyu/RT-DETR

mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

• Paper: https://arxiv.org/abs/2311.04257
• Code: https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2

Link-Context Learning for Multimodal LLMs

• Paper: https://arxiv.org/abs/2308.07891
• Code: https://github.com/isekai-portal/Link-Context-Learning/tree/main

OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

• Paper: https://arxiv.org/abs/2311.17911
• Code: https://github.com/shikiw/OPERA

Making Large Multimodal Models Understand Arbitrary Visual Prompts

• Homepage: https://vip-llava.github.io/
• Paper: https://arxiv.org/abs/2312.00784

Pink: Unveiling the power of referential comprehension for multi-modal llms

• Paper: https://arxiv.org/abs/2310.00582
• Code: https://github.com/SY-Xuan/Pink

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

• Paper: https://arxiv.org/abs/2311.08046
• Code: https://github.com/PKU-YuanGroup/Chat-UniVi

InstanceDiffusion: Instance-level Control for Image Generation

• Homepage: https://people.eecs.berkeley.edu/~xdwang/projects/InstDiff/

• Paper: https://arxiv.org/abs/2402.03290

• Code: https://github.com/frank-xwang/InstanceDiffusion

Residual Denoising Diffusion Models

• Paper: https://arxiv.org/abs/2308.13712
• Code: https://github.com/nachifur/RDDM

DeepCache: Accelerating Diffusion Models for Free

• Paper: https://arxiv.org/abs/2312.00858
• Code: https://github.com/horseee/DeepCache

TransNeXt: Robust Foveal Visual Perception for Vision Transformers

• Paper: https://arxiv.org/abs/2311.17132
• Code: https://github.com/DaiShiResearch/TransNeXt

RepViT: Revisiting Mobile CNN From ViT Perspective

• Paper: https://arxiv.org/abs/2307.09283
• Code: https://github.com/THU-MIG/RepViT

DETRs Beat YOLOs on Real-time Object Detection

• Paper: https://arxiv.org/abs/2304.08069
• Code: https://github.com/lyuwenyu/RT-DETR

Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation

• Paper: https://arxiv.org/abs/2312.01220
• Code: https://github.com/ZPDu/Boosting-Object-Detection-with-Zero-Shot-Day-Night-Domain-Adaptation

YOLO-World: Real-Time Open-Vocabulary Object Detection

• Paper: https://arxiv.org/abs/2401.17270
• Code: https://github.com/AILab-CVC/YOLO-World

Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation

• Paper: https://arxiv.org/abs/2312.04265
• Code: https://github.com/w1oves/Rein

SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation

• Paper: https://arxiv.org/abs/2311.15537
• Code: https://github.com/xb534/SED

Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology

• Paper: https://arxiv.org/abs/2402.17228
• Code: https://github.com/DearCaat/RRT-MIL

VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis

• Paper: https://arxiv.org/abs/2402.17300
• Code: https://github.com/Luffy03/VoCo

ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images

• Paper: https://arxiv.org/abs/2311.15264
• Code: https://github.com/nicoboou/chada_vit

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

• Paper: https://arxiv.org/abs/2310.08370
• Code: https://github.com/Nightmare-n/UniPAD

Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications

• Paper: https://arxiv.org/abs/2311.17663
• Code: https://github.com/haomo-ai/Cam4DOcc

Memory-based Adapters for Online 3D Scene Perception

• Paper: https://arxiv.org/abs/2403.06974
• Code: https://github.com/xuxw98/Online3D

Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

• Paper: https://arxiv.org/abs/2306.15670
• Code: https://github.com/hustvl/Symphonies

A Real-world Large-scale Dataset for Roadside Cooperative Perception

• Paper: https://arxiv.org/abs/2403.10145
• Code: https://github.com/AIR-THU/DAIR-RCooper

PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection

• Paper: https://arxiv.org/abs/2312.08371
• Code: https://github.com/kuanchihhuang/PTT

UniMODE: Unified Monocular 3D Object Detection

• Paper: https://arxiv.org/abs/2402.18573

Edit One for All: Interactive Batch Image Editing

• Homepage: https://thaoshibe.github.io/edit-one-for-all
• Paper: https://arxiv.org/abs/2401.10219
• Code: https://github.com/thaoshibe/edit-one-for-all

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

• Homepage: https://maskint.github.io

• Paper: https://arxiv.org/abs/2312.12468

Residual Denoising Diffusion Models

• Paper: https://arxiv.org/abs/2308.13712
• Code: https://github.com/nachifur/RDDM

Boosting Image Restoration via Priors from Pre-trained Models

• Paper: https://arxiv.org/abs/2403.06793

SeD: Semantic-Aware Discriminator for Image Super-Resolution

• Paper: https://arxiv.org/abs/2402.19387
• Code: https://github.com/lbc12345/SeD

InstanceDiffusion: Instance-level Control for Image Generation

• Homepage: https://people.eecs.berkeley.edu/~xdwang/projects/InstDiff/

• Paper: https://arxiv.org/abs/2402.03290

• Code: https://github.com/frank-xwang/InstanceDiffusion

ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations

• Homepage: https://eclipse-t2i.vercel.app/

• Paper: https://arxiv.org/abs/2312.04655

• Code: https://github.com/eclipse-t2i/eclipse-inference

Instruct-Imagen: Image Generation with Multi-modal Instruction

• Paper: https://arxiv.org/abs/2401.01952

Residual Denoising Diffusion Models

• Paper: https://arxiv.org/abs/2308.13712
• Code: https://github.com/nachifur/RDDM

UniGS: Unified Representation for Image Generation and Segmentation

• Paper: https://arxiv.org/abs/2312.01985

Multi-Instance Generation Controller for Text-to-Image Synthesis

• Paper: https://arxiv.org/abs/2402.05408
• Code: https://github.com/limuloo/migc

Vlogger: Make Your Dream A Vlog

• Paper: https://arxiv.org/abs/2401.09414
• Code: https://github.com/Vchitect/Vlogger

VBench: Comprehensive Benchmark Suite for Video Generative Models

• Homepage: https://vchitect.github.io/VBench-project/

• Paper: https://arxiv.org/abs/2311.17982

• Code: https://github.com/Vchitect/VBench

MVBench: A Comprehensive Multi-modal Video Understanding Benchmark

• Paper: https://arxiv.org/abs/2311.17005
• Code: https://github.com/OpenGVLab/Ask-Anything/tree/main/video_chat2

Logit Standardization in Knowledge Distillation

• Paper: https://arxiv.org/abs/2403.01427
• Code: https://github.com/sunshangquan/logit-standardization-KD

Efficient Dataset Distillation via Minimax Diffusion

• Paper: https://arxiv.org/abs/2311.15529
• Code: https://github.com/vimar-gu/MinimaxDiffusion

KVQ: Kaleidoscope Video Quality Assessment for Short-form Videos

• Homepage: https://lixinustc.github.io/projects/KVQ/

• Paper: https://arxiv.org/abs/2402.07220

• Code: https://github.com/lixinustc/KVQ-Challenge-CVPR-NTIRE2024

A Real-world Large-scale Dataset for Roadside Cooperative Perception

• Paper: https://arxiv.org/abs/2403.10145
• Code: https://github.com/AIR-THU/DAIR-RCooper

Object Recognition as Next Token Prediction

• Paper: https://arxiv.org/abs/2312.02142
• Code: https://github.com/kaiyuyue/nxtp

ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks

• Paper: https://arxiv.org/abs/2306.14525
• Code: https://parameternet.github.io/

Seamless Human Motion Composition with Blended Positional Encodings

• Paper: https://arxiv.org/abs/2402.15509
• Code: https://github.com/BarqueroGerman/FlowMDM

LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning

• Homepage: https://ll3da.github.io/

• Paper: https://arxiv.org/abs/2311.18651

• Code: https://github.com/Open3DA/LL3DA

CLOVA: A Closed-LOop Visual Assistant with Tool Usage and Update

• Homepage: https://clova-tool.github.io/
• Paper: https://arxiv.org/abs/2312.10908

MoMask: Generative Masked Modeling of 3D Human Motions

• Paper: https://arxiv.org/abs/2312.00063
• Code: https://github.com/EricGuo5513/momask-codes

Amodal Ground Truth and Completion in the Wild

• Homepage: https://www.robots.ox.ac.uk/~vgg/research/amodal/
• Paper: https://arxiv.org/abs/2312.17247
• Code: https://github.com/Championchess/Amodal-Completion-in-the-Wild

Improved Visual Grounding through Self-Consistent Explanations

• Paper: https://arxiv.org/abs/2312.04554
• Code: https://github.com/uvavision/SelfEQ