CVPR 2024

Research Paper with Code

---

Table of Contents

• 3DGS (Gaussian Splatting)
• Avatars
• Backbone
• CLIP
• Embodied AI
• OCR
• NeRF
• DETR
• ReID
• Long-Tail
• Vision Transformer
• Vision-Language
• Self-supervised Learning
• Data Augmentation
• Object Detection
• Anomaly Detection
• Visual Tracking
• Semantic Segmentation
• Instance Segmentation
• Panoptic Segmentation
• Medical Image
• Medical Image Segmentation
• Video Object Segmentation
• Video Instance Segmentation
• Referring Image Segmentation
• Image Matting
• Image Editing
• Low-level Vision
• Super-Resolution
• Denoising
• Deblur
• Autonomous Driving
• 3D Point Cloud
• 3D Object Detection
• 3D Semantic Segmentation
• 3D Object Tracking
• 3D Semantic Scene Completion
• 3D Registration
• 3D Human Pose Estimation
• 3D Human Mesh Estimation
• Image Generation
• Video Generation
• Video Understanding
• Knowledge Distillation
• Stereo Matching
• Scene Graph Generation
• Video Quality Assessment
• Datasets
• Others

Domain-wise Table

3DGS (Gaussian Splatting)

Index	Paper Title	Paper Link	Code	Official Repo
1	Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering	Paper	Code	Homepage
2	GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis	Paper	Code	Homepage
3	GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians	Paper	Code	N/A
4	GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting	Paper	Code	N/A
5	Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction	Paper	Code	Homepage

Avatars

Index	Paper Title	Paper Link	Code	Official Repo
6	GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians	Paper	Code	N/A
7	Real-Time Simulated Avatar from Head-Mounted Sensors	Paper	N/A	Homepage

Backbone

Index	Paper Title	Paper Link	Code	Official Repo
8	RepViT: Revisiting Mobile CNN From ViT Perspective	Paper	Code	N/A
9	TransNeXt: Robust Foveal Visual Perception for Vision Transformers	Paper	Code	N/A

CLIP

Index	Paper Title	Paper Link	Code	Official Repo
10	Alpha-CLIP: A CLIP Model Focusing on Wherever You Want	Paper	Code	N/A
11	FairCLIP: Harnessing Fairness in Vision-Language Learning	Paper	Code	N/A

Embodied AI

Index	Paper Title	Paper Link	Code	Official Repo
12	EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI	Paper	Code	Homepage
13	MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception	Paper	Code	Homepage

OCR

Index	Paper Title	Paper Link	Code	Official Repo
14	An Empirical Study of Scaling Law for OCR	Paper	Code	N/A
15	ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting	Paper	Code	N/A

NeRF

Index	Paper Title	Paper Link	Code	Official Repo
16	PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF	Paper	Code	N/A

DETR

Index	Paper Title	Paper Link	Code	Official Repo
17	DETRs Beat YOLOs on Real-time Object Detection	Paper	Code	N/A
18	Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement	Paper	Code	N/A

ReID

Index	Paper Title	Paper Link	Code	Official Repo
19	Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification	Paper	Code	N/A
20	Noisy-Correspondence Learning for Text-to-Image Person Re-identification	Paper	Code	N/A

Long-Tail

Index	Paper Title	Paper Link	Code	Official Repo
1	Delving into the Trajectory Long-tail Distribution for Multi-object Tracking	Paper	Code	N/A

Vision Transformer

Index	Paper Title	Paper Link	Code	Official Repo
2	TransNeXt: Robust Foveal Visual Perception for Vision Transformers	Paper	Code	N/A
3	RepViT: Revisiting Mobile CNN From ViT Perspective	Paper	Code	N/A

Vision-Language

Index	Paper Title	Paper Link	Code	Official Repo
4	PromptKD: Unsupervised Prompt Distillation for Vision-Language Models	Paper	Code	N/A
5	FairCLIP: Harnessing Fairness in Vision-Language Learning	Paper	Code	N/A

Self-supervised Learning

Index	Paper Title	Paper Link	Code	Official Repo
6	N/A	N/A	N/A	N/A

Data Augmentation

Index	Paper Title	Paper Link	Code	Official Repo
7	N/A	N/A	N/A	N/A

Object Detection

Index	Paper Title	Paper Link	Code	Official Repo
8	DETRs Beat YOLOs on Real-time Object Detection	Paper	Code	N/A
9	Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation	Paper	Code	N/A
10	YOLO-World: Real-Time Open-Vocabulary Object Detection	Paper	Code	N/A
11	Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement	Paper	Code	N/A

Anomaly Detection

Index	Paper Title	Paper Link	Code	Official Repo
12	Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection	Paper	Code	N/A

Visual Tracking

Index	Paper Title	Paper Link	Code	Official Repo
13	N/A	N/A	N/A	N/A

Semantic Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
14	Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation	Paper	Code	N/A
15	SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation	Paper	Code	N/A

Instance Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
16	N/A	N/A	N/A	N/A

Panoptic Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
17	N/A	N/A	N/A	N/A

Medical Image

Index	Paper Title	Paper Link	Code	Official Repo
18	Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology	Paper	Code	N/A
19	VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis	Paper	Code	N/A
20	ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images	Paper	Code	N/A

Medical Image Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
21	N/A	N/A	N/A	N/A

Video Object Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
22	N/A	N/A	N/A	N/A

Video Instance Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
23	N/A	N/A	N/A	N/A

Referring Image Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
24	N/A	N/A	N/A	N/A

Image Matting

Index	Paper Title	Paper Link	Code	Official Repo
25	N/A	N/A	N/A	N/A

Image Editing

Index	Paper Title	Paper Link	Code	Official Repo
26	Edit One for All: Interactive Batch Image Editing	Paper	Code	Homepage

Low-level Vision

Index	Paper Title	Paper Link	Code	Official Repo
27	Residual Denoising Diffusion Models	Paper	Code	N/A
28	Boosting Image Restoration via Priors from Pre-trained Models	Paper	N/A	N/A

Super-Resolution)

Index	Paper Title	Paper Link	Code	Official Repo
29	SeD: Semantic-Aware Discriminator for Image Super-Resolution	Paper	Code	N/A
30	APISR: Anime Production Inspired Real-World Anime Super-Resolution	Paper	[Code](https://github.com/Kiter### Domain-wise Table

Denoising

Index	Paper Title	Paper Link	Code	Official Repo
31	Residual Denoising Diffusion Models	Paper	Code	N/A

Deblur

Index	Paper Title	Paper Link	Code	Official Repo
32	N/A	N/A	N/A	N/A

Autonomous Driving

Index	Paper Title	Paper Link	Code	Official Repo
33	UniPAD: A Universal Pre-training Paradigm for Autonomous Driving	Paper	Code	N/A
34	Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications	Paper	Code	N/A
35	Memory-based Adapters for Online 3D Scene Perception	Paper	Code	N/A
36	Symphonize 3D Semantic Scene Completion with Contextual Instance Queries	Paper	Code	N/A
37	A Real-world Large-scale Dataset for Roadside Cooperative Perception	Paper	Code	N/A
38	Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving	Paper	Code	N/A

3D Point Cloud

Index	Paper Title	Paper Link	Code	Official Repo
40	N/A	N/A	N/A	N/A

3D Object Detection

Index	Paper Title	Paper Link	Code	Official Repo
41	PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection	Paper	Code	N/A
42	UniMODE: Unified Monocular 3D Object Detection	Paper	N/A	N/A

3D Semantic Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
43	N/A	N/A	N/A	N/A

3D Object Tracking

Index	Paper Title	Paper Link	Code	Official Repo
44	N/A	N/A	N/A	N/A

3D Semantic Scene Completion

Index	Paper Title	Paper Link	Code	Official Repo
45	Symphonize 3D Semantic Scene Completion with Contextual Instance Queries	Paper	Code	N/A

3D Registration

Index	Paper Title	Paper Link	Code	Official Repo
46	N/A	N/A	N/A	N/A

3D Human Pose Estimation

Index	Paper Title	Paper Link	Code	Official Repo
47	Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation	Paper	Code	N/A

3D Human Mesh Estimation

Index	Paper Title	Paper Link	Code	Official Repo
48	N/A	N/A	N/A	N/A

Medical Image

Index	Paper Title	Paper Link	Code	Official Repo
49	Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology	Paper	Code	N/A
50	VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis	Paper	Code	N/A
51	ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images	Paper	Code	N/A

Image Generation

Index	Paper Title	Paper Link	Code	Official Repo
52	InstanceDiffusion: Instance-level Control for Image Generation	Paper	Code	Homepage
53	ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations	Paper	Code	Homepage
54	Instruct-Imagen: Image Generation with Multi-modal Instruction	Paper	N/A	N/A
55	UniGS: Unified Representation for Image Generation and Segmentation	Paper	N/A	N/A
56	Multi-Instance Generation Controller for Text-to-Image Synthesis	Paper	Code	N/A
57	SVGDreamer: Text Guided SVG Generation with Diffusion Model	Paper	Code	N/A
58	InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model	Paper	Code	N/A
59	Ranni: Taming Text-to-Image Diffusion for Accurate Prompt Following	Paper	Code	N/A

Video Generation

Index	Paper Title	Paper Link	Code	Official Repo
60	Vlogger: Make Your Dream A Vlog	Paper	Code	N/A
61	VBench: Comprehensive Benchmark Suite for Video Generative Models	Paper	Code	Homepage
62	VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models	Paper	Code	Homepage

Vision Transformer

Index	Paper Title	Paper Link	Code	Official Repo
63	TransNeXt: Robust Foveal Visual Perception for Vision Transformers	Paper	Code	N/A
64	RepViT: Revisiting Mobile CNN From ViT Perspective	Paper	Code	N/A
65	A General and Efficient Training for Transformer via Token Expansion	Paper	Code	N/A

Vision-Language

Index	Paper Title	Paper Link	Code	Official Repo
66	PromptKD: Unsupervised Prompt Distillation for Vision-Language Models	Paper	Code	N/A
67	FairCLIP: Harnessing Fairness in Vision-Language Learning	Paper	Code	N/A

Object Detection

Index	Paper Title	Paper Link	Code	Official Repo
68	DETRs Beat YOLOs on Real-time Object Detection	Paper	Code	N/A
69	Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation	Paper	Code	N/A
70	YOLO-World: Real-Time Open-Vocabulary Object Detection	Paper	Code	N/A
71	Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement	Paper	Code	N/A

Anomaly Detection

Index	Paper Title	Paper Link	Code	Official Repo
72	Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection	Paper	Code	N/A

Object Tracking

Index	Paper Title	Paper Link	Code	Official Repo
73	Delving into the Trajectory Long-tail Distribution for Multi-object Tracking	Paper	Code	N/A

Semantic Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
74	Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation	Paper	Code	N/A
75	SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation	Paper	Code	N/A

Medical Image

Index	Paper Title	Paper Link	Code	Official Repo
76	Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology	Paper	Code	N/A
77	VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis	Paper	Code	N/A
78	ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images	Paper	Code	N/A

Medical Image Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
76	N/A	N/A	N/A	N/A

Autonomous Driving

Index	Paper Title	Paper Link	Code	Official Repo
77	UniPAD: A Universal Pre-training Paradigm for Autonomous Driving	Paper	Code	N/A
78	Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications	Paper	Code	N/A
79	Memory-based Adapters for Online 3D Scene Perception	Paper	Code	N/A
80	Symphonize 3D Semantic Scene Completion with Contextual Instance Queries	Paper	Code	N/A
81	A Real-world Large-scale Dataset for Roadside Cooperative Perception	Paper	Code	N/A
82	Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving	Paper	Code	N/A
83	Traffic Scene Parsing through the TSP6K Dataset	Paper	Code	N/A

3D Point Cloud

Index	Paper Title	Paper Link	Code	Official Repo
84	N/A	N/A	N/A	N/A

3D Object Detection

Index	Paper Title	Paper Link	Code	Official Repo
85	PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection	Paper	Code	N/A
86	UniMODE: Unified Monocular 3D Object Detection	Paper	N/A	N/A

3D Semantic Segmentation

Index	Paper Title	Paper Link	Code	Official Repo
87	N/A	N/A	N/A	N/A

Image Editing

Index	Paper Title	Paper Link	Code	Official Repo
88	Edit One for All: Interactive Batch Image Editing	Paper	Code	Homepage

Video Editing

Index	Paper Title	Paper Link	Code	Official Repo
89	MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers	Paper	N/A	Homepage

Low-level Vision

Index	Paper Title	Paper Link	Code	Official Repo
90	Residual Denoising Diffusion Models	Paper	Code	N/A
91	Boosting Image Restoration via Priors from Pre-trained Models	Paper	N/A	N/A

Super-Resolution

Index	Paper Title	Paper Link	Code	Official Repo
92	SeD: Semantic-Aware Discriminator for Image Super-Resolution	Paper	Code	N/A
93	APISR: Anime Production Inspired Real-World Anime Super-Resolution	Paper	Code	N/A

Denoising

Index	Paper Title	Paper Link	Code	Official Repo
94	N/A	N/A	N/A	N/A

3D Human Pose Estimation

Index	Paper Title	Paper Link	Code	Official Repo
95	Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation	Paper	Code	N/A

Image Generation

Index	Paper Title	Paper Link	Code	Official Repo
96	InstanceDiffusion: Instance-level Control for Image Generation	Paper	Code	Homepage
97	ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations	Paper	Code	Homepage
98	Instruct-Imagen: Image Generation with Multi-modal Instruction	Paper	N/A	N/A
99	Residual Denoising Diffusion Models	Paper	Code	N/A
100	UniGS: Unified Representation for Image Generation and Segmentation	Paper	N/A	N/A
101	Multi-Instance Generation Controller for Text-to-Image Synthesis	Paper	Code	N/A
102	SVGDreamer: Text Guided SVG Generation with Diffusion Model	Paper	Code	N/A
103	InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model	Paper	Code	N/A
104	Ranni: Taming Text-to-Image Diffusion for Accurate Prompt Following	Paper	Code	N/A

Video Generation

Index	Paper Title	Paper Link	Code	Official Repo
105	Vlogger: Make Your Dream A Vlog	Paper	Code	N/A
106	VBench: Comprehensive Benchmark Suite for Video Generative Models	Paper	Code	Homepage
107	VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models	Paper	Code	Homepage

3D Generation

Index	Paper Title	Paper Link	Code	Official Repo
108	CityDreamer: Compositional Generative Model of Unbounded 3D Cities	Paper	Code	Homepage
109	LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching	Paper	Code	N/A

Video Understanding

Index	Paper Title	Paper Link	Code	Official Repo
110	MVBench: A Comprehensive Multi-modal Video Understanding Benchmark	Paper	Code	N/A

Knowledge Distillation

Index	Paper Title	Paper Link	Code	Official Repo
111	Logit Standardization in Knowledge Distillation	Paper	Code	N/A
112	Efficient Dataset Distillation via Minimax Diffusion	Paper	Code	N/A

Stereo Matching

Index	Paper Title	Paper Link	Code	Official Repo
113	Neural Markov Random Field for Stereo Matching	Paper	Code	N/A

Scene Graph Generation

Index	Paper Title	Paper Link	Code	Official Repo
114	HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation	Paper	Code	Homepage

Video Quality Assessment

Index	Paper Title	Paper Link	Code	Official Repo
115	KVQ: Kaleidoscope Video Quality Assessment for Short-form Videos	Paper	Code	Homepage

Datasets

Index	Paper Title	Paper Link	Code	Official Repo
116	A Real-world Large-scale Dataset for Roadside Cooperative Perception	Paper	Code	N/A
117	Traffic Scene Parsing through the TSP6K Dataset	Paper	Code	N/A

Others

Index	Paper Title	Paper Link	Code	Official Repo
118	Object Recognition as Next Token Prediction	Paper	Code	N/A
119	ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks	Paper	Code	N/A
120	Seamless Human Motion Composition with Blended Positional Encodings	Paper	Code	N/A
121	LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning	Paper	Code	Homepage
122	CLOVA: A Closed-LOop Visual Assistant with Tool Usage and Update	Paper	N/A	Homepage
123	MoMask: Generative Masked Modeling of 3D Human Motions	Paper	Code	N/A
124	Amodal Ground Truth and Completion in the Wild	Paper	Code	Homepage
125	Improved Visual Grounding through Self-Consistent Explanations	Paper	Code	N/A
126	ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object	Paper	Code	Homepage
127	Learning from Synthetic Human Group Activities	Paper	Code	Homepage
128	A Cross-Subject Brain Decoding Framework	Paper	Code	Homepage
129	Multi-Task Dense Prediction via Mixture of Low-Rank Experts	Paper	Code	N/A
130	Contrastive Mean-Shift Learning for Generalized Category Discovery	Paper	Code	Homepage

Thank you for Reading