README.md

ICCV2023-Papers-with-Code

ICCV 2023 论文和开源项目合集(papers with code)！

2160 papers accepted！

ICCV 2023 收录论文IDs：https://t.co/A0mCH8gbOi

注1：欢迎各位大佬提交issue，分享ICCV 2023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

ICCV 2021

如果你想了解最新最优质的的CV论文、开源项目和学习资料，欢迎扫码加入【CVer学术交流群】！互相学习，一起进步~

【ICCV 2023 论文开源目录】

• Backbone
• CLIP
• MAE
• GAN
• GNN
• MLP
• NAS
• OCR
• NeRF
• DETR
• Prompt
• Diffusion Models(扩散模型)
• Prompt
• Avatars
• 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)
• 医学图像分类(Medical Image Classfication)
• 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)
• Low-level Vision
• 超分辨率(Super-Resolution)
• 去噪(Denoising)
• 去模糊(Deblur)
• 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)
• 图像编辑(Image Editing)
• 视频编辑(Video Editing)
• 视频理解(Video Understanding)
• 人体运动生成(Human Motion Generation)
• 低光照图像增强(Low-light Image Enhancement)
• 场景文本识别(Scene Text Recognition)
• 图像检索(Image Retrieval)
• 图像融合(Image Fusion)
• 轨迹预测(Trajectory Prediction)
• 人群计数(Crowd Counting)
• Video Quality Assessment(视频质量评价)
• 其它(Others)

Avatars

Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control

Paper: https://arxiv.org/abs/2303.17606

Code: https://github.com/songrise/AvatarCraft

Backbone

Rethinking Mobile Block for Efficient Attention-based Models

• Paper: https://arxiv.org/abs/2301.01146
• Code: https://github.com/zhangzjn/EMO

CLIP

PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization

• Paper: https://arxiv.org/abs/2307.15199
• Code: https://PromptStyler.github.io/

CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation

• Paper: https://arxiv.org/abs/2308.15226
• Code: http://www.github.com/devaansh100/CLIPTrans

NeRF

IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis

• Homepage: https://zju3dv.github.io/intrinsic_nerf/
• Paper: https://arxiv.org/abs/2210.00647
• Code: https://github.com/zju3dv/IntrinsicNeRF

Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control

• Paper: https://arxiv.org/abs/2303.17606

• Code: https://github.com/songrise/AvatarCraft

FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis

• Homepage: https://shawn615.github.io/flipnerf/
• Code: https://github.com/shawn615/FlipNeRF
• Paper: https://arxiv.org/abs/2306.17723

Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields

• Homepage: https://wbhu.github.io/projects/Tri-MipRF

• Paper: https://arxiv.org/abs/2307.11335

• Code: https://github.com/wbhu/Tri-MipRF

Diffusion Models(扩散模型)

PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

• Paper: https://arxiv.org/abs/2306.15667
• Code: https://github.com/facebookresearch/PoseDiffusion

FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

• Paper: https://arxiv.org/abs/2303.09833
• Code: https://github.com/vvictoryuki/FreeDoM

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

• Paper: https://arxiv.org/abs/2307.10816
• Code: https://github.com/Sierkinhane/BoxDiff

BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction

• Paper: https://arxiv.org/abs/2211.14304
• Code: https://github.com/BarqueroGerman/BeLFusion

DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion

• Paper: https://arxiv.org/abs/2303.06840
• Code: https://github.com/Zhaozixiang1228/MMIF-DDFM

DIRE for Diffusion-Generated Image Detection

• Paper: https://arxiv.org/abs/2303.09295
• Code: https://github.com/ZhendongWang6/DIRE

Prompt

Read-only Prompt Optimization for Vision-Language Few-shot Learning

• Paper: https://arxiv.org/abs/2308.14960
• Code: https://github.com/mlvlab/RPO

Introducing Language Guidance in Prompt-based Continual Learning

• Paper: https://arxiv.org/abs/2308.15827
• Code: None

视觉和语言(Vision-Language)

Read-only Prompt Optimization for Vision-Language Few-shot Learning

• Paper: https://arxiv.org/abs/2308.14960
• Code: https://github.com/mlvlab/RPO

目标检测(Object Detection)

Femtodet: an object detection baseline for energy versus performance tradeoffs

• Paper: https://arxiv.org/abs/2301.06719
• Code: https://github.com/yh-pengtu/FemtoDet

Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment

• Paper: https://arxiv.org/abs/2207.13085
• Code: https://github.com/Atten4Vis/GroupDETR

Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection

• Paper: https://arxiv.org/abs/2205.09613
• Code: https://github.com/LiewFeng/imTED

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

• Paper: https://arxiv.org/abs/2308.09242
• Code: https://github.com/iSEE-Laboratory/ASAG

目标跟踪(Visual Tracking)

Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers

• Paper: https://arxiv.org/abs/2307.04129
• Code: https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker

语义分割(Semantic Segmentation)

Segment Anything

• Homepage: https://segment-anything.com/
• Paper: https://arxiv.org/abs/2304.02643
• Code: https://github.com/facebookresearch/segment-anything

MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation

• Paper: https://arxiv.org/abs/2304.09913
• Code: https://github.com/shjo-april/MARS

FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation

• Paper: https://arxiv.org/abs/2307.07245
• Code: https://github.com/TY-Shi/FreeCOS

Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation

• Paper: https://arxiv.org/abs/2211.14512
• Code: https://github.com/yyliu01

Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement

• Paper: https://arxiv.org/abs/2307.09362
• Code: https://github.com/w1oves/DTP

视频目标分割(Video Object Segmentation)

Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus

• Paper: https://arxiv.org/abs/2207.01203

• Code: https://github.com/lxa9867/R2VOS

视频实例分割(Video Instance Segmentation)

DVIS: Decoupled Video Instance Segmentation Framework

• Paper: https://arxiv.org/abs/2306.03413
• Code: https://github.com/zhang-tao-whu/DVIS

医学图像分类

BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification

• Paper: https://arxiv.org/abs/2203.01937

• Code: https://github.com/cyh-0/BoMD

医学图像分割

CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection

• Paper: https://arxiv.org/abs/2301.00785
• Code: https://github.com/ljwztc/CLIP-Driven-Universal-Model

Low-level Vision

Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive

• Paper: https://arxiv.org/abs/2305.19862
• Code: https://github.com/shangwei5/SelfDRSC

超分辨率(Super-Resolution)

Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution.

• Paper: https://arxiv.org/abs/2303.08942
• Code: https://github.com/Zhaozixiang1228/GDSR-SSDNet

3D点云(3D Point Cloud)

Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

• Homepage: https://ldkong.com/Robo3D
• Paper: https://arxiv.org/abs/2303.17597
• Code: https://github.com/ldkong1205/Robo3D

Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models

• Paper: https://arxiv.org/abs/2304.07221
• Code: https://github.com/zyh16143998882/ICCV23-IDPT

Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos

• Paper: https://arxiv.org/abs/2308.09247
• Code: None

3D目标检测(3D Object Detection)

PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

• Paper: https://arxiv.org/abs/2206.01256
• Code: https://github.com/megvii-research/PETR

DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection

• Paper: https://arxiv.org/abs/2304.13031
• Code: https://github.com/AIR-DISCOVER/DQS3D

SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection

• Paper: https://arxiv.org/abs/2304.14340
• Code: https://github.com/yichen928/SparseFusion

StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

• Paper: https://arxiv.org/abs/2303.11926
• Code: https://github.com/exiawsh/StreamPETR.git

Cross Modal Transformer: Towards Fast and Robust 3D Object Detection

• Paper: https://arxiv.org/abs/2301.01283
• Code: https://github.com/junjie18/CMT.git

MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation

• Paper: https://arxiv.org/abs/2304.09801
• Project: https://chongjiange.github.io/metabev.html
• Code: https://github.com/ChongjianGE/MetaBEV

Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling

• Paper: https://arxiv.org/abs/2307.07944
• Code: https://github.com/zhuoxiao-chen/ReDB-DA-3Ddet

SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection

• Paper: https://arxiv.org/abs/2307.11477
• Code: https://github.com/mengtan00/SA-BEV

3D语义分割(3D Semantic Segmentation)

Rethinking Range View Representation for LiDAR Segmentation

• Homepage: https://ldkong.com/RangeFormer
• Paper: https://arxiv.org/abs/2303.05367
• Code: None

3D目标跟踪(3D Object Tracking)

MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors

• Paper: https://arxiv.org/abs/2303.05071
• Code : https://github.com/slothfulxtx/MBPTrack3D

视频理解(Video Understanding)

Unmasked Teacher: Towards Training-Efficient Video Foundation Models

• Paper: https://arxiv.org/abs/2303.16058

• Code: https://github.com/OpenGVLab/unmasked_teacher

图像生成(Image Generation)

FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

• Paper: https://arxiv.org/abs/2303.09833
• Code: https://github.com/vvictoryuki/FreeDoM

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

• Paper: https://arxiv.org/abs/2307.10816
• Code: https://github.com/Sierkinhane/BoxDiff

视频生成(Video Generation)

Simulating Fluids in Real-World Still Images

• Homepage: https://slr-sfs.github.io/
• Paper: https://arxiv.org/abs/2204.11335
• Code: https://github.com/simon3dv/SLR-SFS

图像编辑(Image Editing)

Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing

• Paper: https://arxiv.org/abs/2304.02051
• Code: https://github.com/aimagelab/multimodal-garment-designer

视频编辑(Video Editing)

FateZero: Fusing Attentions for Zero-shot Text-based Video Editing

• Project: https://fate-zero-edit.github.io/
• Paper: https://arxiv.org/abs/2303.09535
• Code: https://github.com/ChenyangQiQi/FateZero

人体运动生成(Human Motion Generation)

BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction

• Paper: https://arxiv.org/abs/2211.14304
• Code: https://github.com/BarqueroGerman/BeLFusion

低光照图像增强(Low-light Image Enhancement)

Implicit Neural Representation for Cooperative Low-light Image Enhancement

• Paper: https://arxiv.org/abs/2303.11722
• Code: https://github.com/Ysz2022/NeRCo

场景文本检测(Scene Text Detection)

场景文本识别(Scene Text Recognition)

Self-supervised Character-to-Character Distillation for Text Recognition

• Paper: https://arxiv.org/abs/2211.00288
• Code: https://github.com/TongkunGuan/CCD

MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition

• Paper: https://arxiv.org/abs/2305.14758
• Code: https://github.com/simplify23/MRN
• 中文解读：https://zhuanlan.zhihu.com/p/643948935

图像检索(Image Retrieval)

Zero-Shot Composed Image Retrieval with Textual Inversion

• Paper: https://arxiv.org/abs/2303.15247
• Code: https://github.com/miccunifi/SEARLE

图像融合(Image Fusion)

DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion

• Paper: https://arxiv.org/abs/2303.06840
• Code: https://github.com/Zhaozixiang1228/MMIF-DDFM

轨迹预测(Trajectory Prediction)

EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting

• Homepage: https://inhwanbae.github.io/publication/eigentrajectory/

• Paper: https://arxiv.org/abs/2307.09306

• Code: https://github.com/InhwanBae/EigenTrajectory

人群计数(Crowd Counting)

Point-Query Quadtree for Crowd Counting, Localization, and More

• Paper: https://arxiv.org/abs/2308.13814
• Code: https://github.com/cxliu0/PET

Video Quality Assessment(视频质量评价)

Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives

• Paper: https://arxiv.org/abs/2211.04894
• Code: https://github.com/VQAssessment/DOVER

其它(Others)

MotionBERT: A Unified Perspective on Learning Human Motion Representations

• Homepage: https://motionbert.github.io/
• Paper: https://arxiv.org/abs/2210.06551
• Code: https://github.com/Walter0807/MotionBERT

Graph Matching with Bi-level Noisy Correspondence

• Paper: https://arxiv.org/pdf/2212.04085.pdf
• Code: https://github.com/Lin-Yijie/Graph-Matching-Networks/tree/main/COMMON

LDL: Line Distance Functions for Panoramic Localization

• Paper: https://arxiv.org/abs/2308.13989
• Code: https://github.com/82magnolia/panoramic-localization

Active Neural Mapping

• Homepage: https://zikeyan.github.io/active-INR/index.html
• Paper: https://arxiv.org/abs/2308.16246
• Code: https://zikeyan.github.io/active-INR/index.html#

Reconstructing Groups of People with Hypergraph Relational Reasoning

• Paper: https://arxiv.org/abs/2308.15844
• Code: https://github.com/boycehbz/GroupRec