☪️添加微信: nvshenj125, 备注方向，进交流学习群

欢迎关注公众号：AI算法与图像处理

🌟 CVPR 2024 持续更新最新论文/paper和相应的开源代码/code！

B站demo：https://space.bilibili.com/288489574

✋ ​注：欢迎各位大佬提交issue，分享CVPR 2022论文/paper和开源项目！共同完善这个项目

往年顶会论文汇总：

CVPR2021

CVPR2022

CVPR2023

ICCV2021

ECCV2022

CVPR 2024 论文/paper交流群已成立！已经收录的同学，可以添加微信：nvshenj125，请备注：CVPR+姓名+学校/公司名称！一定要根据格式申请，可以拉你进群。

返回目录/back

HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative

• 论文/Paper: http://arxiv.org/pdf/2403.02640
• 代码/Code: None

Traffic Scene Parsing through the TSP6K Dataset

• 论文/Paper: https://arxiv.org/pdf/2303.02835.pdf
• 代码/Code: https://github.com/PengtaoJiang/TSP6K

返回目录/back

Balancing Act: Distribution-Guided Debiasing in Diffusion Models

• 论文/Paper: http://arxiv.org/pdf/2402.18206
• 代码/Code: None

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

• 论文/Paper: http://arxiv.org/pdf/2402.19481
• 代码/Code: https://github.com/mit-han-lab/distrifuser

DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly

• 论文/Paper: http://arxiv.org/pdf/2402.19302
• 代码/Code: https://github.com/iit-pavis/diffassemble

Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks

• 论文/Paper: http://arxiv.org/pdf/2403.00644
• 代码/Code: None

Few-shot Learner Parameterization by Diffusion Time-steps

• 论文/Paper: http://arxiv.org/pdf/2403.02649
• 代码/Code: https://github.com/yue-zhongqi/tif

MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant

• 论文/Paper: http://arxiv.org/pdf/2403.04290
• 代码/Code: None

DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations

• 论文/Paper: https://arxiv.org/abs/2403.06951
• 代码/Code: https://github.com/Tianhao-Qi/DEADiff_code

Face2Diffusion for Fast and Editable Face Personalization

• 论文/Paper: http://arxiv.org/pdf/2403.05094
• 代码/Code: https://github.com/mapooon/Face2Diffusion

DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations

• 论文/Paper: http://arxiv.org/pdf/2403.06951
• 代码/Code: None

MACE: Mass Concept Erasure in Diffusion Models

• 论文/Paper: http://arxiv.org/pdf/2403.06135
• 代码/Code: https://github.com/Shilin-LU/MACE

It's All About Your Sketch: Democratising Sketch Control in Diffusion Models

• 论文/Paper: http://arxiv.org/pdf/2403.07234
• 代码/Code: https://github.com/subhadeepkoley/demosketch2rgb

SemCity: Semantic Scene Generation with Triplane Diffusion

• 论文/Paper: http://arxiv.org/pdf/2403.07773
• 代码/Code: https://github.com/zoomin-lee/semcity

返回目录/back

RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization

• 论文/Paper: http://arxiv.org/pdf/2403.00483
• 代码/Code: None

NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging

• 论文/Paper: http://arxiv.org/pdf/2403.03485
• 代码/Code: https://github.com/univ-esuty/noisecollage

Discriminative Probing and Tuning for Text-to-Image Generation

• 论文/Paper: http://arxiv.org/pdf/2403.04321
• 代码/Code: None

Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation

• 论文/Paper: http://arxiv.org/pdf/2403.05239
• 代码/Code: None

Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation

• 论文/Paper: http://arxiv.org/pdf/2403.06452
• 代码/Code: https://github.com/mulns/Text2QR

Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers

• 论文/Paper: http://arxiv.org/pdf/2403.07214
• 代码/Code: None

返回目录/back

返回目录/back

GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding

• 论文/Paper: http://arxiv.org/pdf/2403.03608
• 代码/Code: None

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

• 论文/Paper: http://arxiv.org/pdf/2403.06912
• 代码/Code: https://github.com/fictionarry/dngaussian

S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes

• 论文/Paper: http://arxiv.org/pdf/2403.06205
• 代码/Code: None

返回目录/back

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models

• 论文/Paper: http://arxiv.org/pdf/2403.02781
• 代码/Code: https://github.com/zhengli97/PromptKD

Logit Standardization in Knowledge Distillation

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

RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features

• 论文/Paper: http://arxiv.org/pdf/2403.05061
• 代码/Code: None

$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections

• 论文/Paper: http://arxiv.org/pdf/2403.06213
• 代码/Code: https://github.com/roymiles/vkd

返回目录/back

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

• 论文/Paper: https://arxiv.org/abs/2312.07472
• 代码/Code: https://github.com/IranQin/MP5
• 主页/Website：https://iranqin.github.io/MP5.github.io/

Polos: Multimodal Metric Learning from Human Feedback for Image Captioning

• 论文/Paper: http://arxiv.org/pdf/2402.18091
• 代码/Code: None

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

• 论文/Paper: http://arxiv.org/pdf/2403.02991
• 代码/Code: None

Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval

• 论文/Paper: http://arxiv.org/pdf/2403.05105
• 代码/Code: https://github.com/hhc1997/L2RM

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric

• 论文/Paper: http://arxiv.org/pdf/2403.07839
• 代码/Code: None

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Matching Framework

• 论文/Paper: http://arxiv.org/pdf/2403.07636
• 代码/Code: https://github.com/hieuphan33/mavl

Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations

• 论文/Paper: http://arxiv.org/pdf/2403.07241
• 代码/Code: None

返回目录/back

Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning

• 论文/Paper: http://arxiv.org/pdf/2403.06122
• 代码/Code: https://github.com/root0yang/blindnet

返回目录/back

返回目录/back

返回目录/back

UniMODE: Unified Monocular 3D Object Detection

• 论文/Paper: http://arxiv.org/pdf/2402.18573
• 代码/Code: None

CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoors Object Detection from Multi-view Images

• 论文/Paper: http://arxiv.org/pdf/2403.04198
• 代码/Code: https://github.com/SerCharles/CN-RMA

Memory-based Adapters for Online 3D Scene Perception

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

Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement

• 论文/Paper: https://arxiv.org/abs/2403.16131

• 代码/Code:https://github.com/xiuqhou/Salience-DETR

Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors

• 论文/Paper: http://arxiv.org/pdf/2403.06093
• 代码/Code: https://github.com/nullmax-vision/QAF2D

SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection

• 论文/Paper: http://arxiv.org/pdf/2403.05817
• 代码/Code: https://github.com/zhanggang001/hednet

返回目录/back

DeconfuseTrack:Dealing with Confusion for Multi-Object Tracking

• 论文/Paper: http://arxiv.org/pdf/2403.02767
• 代码/Code: None

Delving into the Trajectory Long-tail Distribution for Muti-object Tracking

• 论文/Paper: http://arxiv.org/pdf/2403.04700
• 代码/Code: https://github.com/chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT

返回目录/back

返回目录/back

返回目录/back

PEM: Prototype-based Efficient MaskFormer for Image Segmentation

• 论文/Paper: http://arxiv.org/pdf/2402.19422
• 代码/Code: https://github.com/niccolocavagnero/pem

Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2403.06462
• 代码/Code: https://github.com/Gavinwxy/DDFP

Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation

• 论文/Paper: http://arxiv.org/pdf/2403.06247
• 代码/Code: None

返回目录/back

返回目录/back

Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration

• 论文/Paper: http://arxiv.org/pdf/2402.18933
• 代码/Code: None

返回目录/back

Depth-aware Test-Time Training for Zero-shot Video Object Segmentation

• 论文/Paper: http://arxiv.org/pdf/2403.04258
• 代码/Code: None

返回目录/back

返回目录/back

Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery

• 论文/Paper: http://arxiv.org/pdf/2403.05419
• 代码/Code: https://github.com/techmn/satmae_pp

返回目录/back

Representations for Recognition and Retrieval

• 论文/Paper: https://arxiv.org/pdf/2403.07535.pdf
• 代码/Code: https://github.com/Junda24/AFNet

返回目录/back

Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval

• 论文/Paper: http://arxiv.org/pdf/2403.00272
• 代码/Code: None

Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval

• 论文/Paper: http://arxiv.org/pdf/2403.05105
• 代码/Code: https://github.com/hhc1997/L2RM

How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?

• 论文/Paper: http://arxiv.org/pdf/2403.07203
• 代码/Code: None

返回目录/back

SeD: Semantic-Aware Discriminator for Image Super-Resolution

• 论文/Paper: http://arxiv.org/pdf/2402.19387
• 代码/Code: None

Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts

• 论文/Paper: http://arxiv.org/pdf/2402.19215
• 代码/Code: https://github.com/mandalinadagi/wgsr

CAMixerSR: Only Details Need More "Attention"

• 论文/Paper: http://arxiv.org/pdf/2402.19289
• 代码/Code: https://github.com/icandle/camixersr

Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning

• 论文/Paper: http://arxiv.org/pdf/2403.02601
• 代码/Code: None

返回目录/back

Boosting Image Restoration via Priors from Pre-trained Models

• 论文/Paper: http://arxiv.org/pdf/2403.06793
• 代码/Code: None

返回目录/back

返回目录/back

Doubly Abductive Counterfactual Inference for Text-based Image Editing

• 论文/Paper: http://arxiv.org/pdf/2403.02981
• 代码/Code: https://github.com/xuesong39/DAC

返回目录/back

返回目录/back

A Unified Framework for Microscopy Defocus Deblur with Multi-Pyramid Transformer and Contrastive Learning

• 论文/Paper: http://arxiv.org/pdf/2403.02611
• 代码/Code: https://github.com/PieceZhang/MPT-CataBlur

返回目录/back

Abductive Ego-View Accident Video Understanding for Safe Driving Perception

• 论文/Paper: http://arxiv.org/pdf/2403.00436
• 代码/Code: None

Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving

• 论文/Paper: http://arxiv.org/pdf/2403.07535
• 代码/Code: website:https://github.com/Junda24/AFNet/

返回目录/back

返回目录/back

返回目录/back

Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing

• 论文/Paper: http://arxiv.org/pdf/2402.19298
• 代码/Code: https://github.com/omggggg/mmdg

返回目录/back

返回目录/back

返回目录/back

返回目录/back

返回目录/back

返回目录/back

FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation

• 论文/Paper: http://arxiv.org/pdf/2403.03221
• 代码/Code: None

Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation

• 论文/Paper: http://arxiv.org/pdf/2403.04381
• 代码/Code: https://github.com/MickeyLLG/S2DHand

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

• 论文/Paper: https://arxiv.org/pdf/2311.12028.pdf
• 代码/Code: https://github.com/NationalGAILab/HoT

返回目录/back

返回目录/back

返回目录/back

返回目录/back

返回目录/back

UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Data Sets

• 论文/Paper: http://arxiv.org/pdf/2403.05086
• 代码/Code: https://github.com/Youngju-Na/UFORecon

DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction

• 论文/Paper: http://arxiv.org/pdf/2403.05005
• 代码/Code: None

Memory-based Adapters for Online 3D Scene Perception

• 论文/Paper: http://arxiv.org/pdf/2403.06974
• 代码/Code: None

Bayesian Diffusion Models for 3D Shape Reconstruction

• 论文/Paper: http://arxiv.org/pdf/2403.06973
• 代码/Code: None

返回目录/back

返回目录/back

Rethinking Few-shot 3D Point Cloud Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2403.00592
• 代码/Code: https://github.com/ZhaochongAn/COSeg

Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension

• 论文/Paper: http://arxiv.org/pdf/2403.03532
• 代码/Code: https://github.com/liuquan98/eyoc

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds

• 论文/Paper: http://arxiv.org/pdf/2403.05247
• 代码/Code: https://github.com/TRLou/HiT-ADV

返回目录/back

Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts

• 论文/Paper: http://arxiv.org/pdf/2403.06495
• 代码/Code: https://github.com/mala-lab/inctrl

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection

• 论文/Paper: http://arxiv.org/pdf/2403.05897
• 代码/Code: https://github.com/cnulab/realnet

返回目录/back

DisCo: Disentangled Control for Realistic Human Dance Generation

• 论文/Paper: https://arxiv.org/abs/2307.00040
• 代码/Code: https://github.com/Wangt-CN/DisCo

Gradient Reweighting: Towards Imbalanced Class-Incremental Learning

• 论文/Paper: http://arxiv.org/pdf/2402.18528
• 代码/Code: None

TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding

• 论文/Paper: http://arxiv.org/pdf/2402.18490
• 代码/Code: None

Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting

• 论文/Paper: http://arxiv.org/pdf/2402.18330
• 代码/Code: https://github.com/tho-kn/egotap

Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing

• 论文/Paper: http://arxiv.org/pdf/2402.18277
• 代码/Code: None

Misalignment-Robust Frequency Distribution Loss for Image Transformation

• 论文/Paper: http://arxiv.org/pdf/2402.18192
• 代码/Code: https://github.com/eezkni/FDL

3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling

• 论文/Paper: http://arxiv.org/pdf/2402.18146
• 代码/Code: https://github.com/jiangchaokang/3dsflabelling

OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction

• 论文/Paper: http://arxiv.org/pdf/2402.18140
• 代码/Code: None

UniVS: Unified and Universal Video Segmentation with Prompts as Queries

• 论文/Paper: http://arxiv.org/pdf/2402.18115
• 代码/Code: https://github.com/minghanli/univs

Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis

• 论文/Paper: http://arxiv.org/pdf/2402.18078
• 代码/Code: https://github.com/YanzuoLu/CFLD

Boosting Neural Representations for Videos with a Conditional Decoder

• 论文/Paper: http://arxiv.org/pdf/2402.18152
• 代码/Code: None

Classes Are Not Equal: An Empirical Study on Image Recognition Fairness

• 论文/Paper: http://arxiv.org/pdf/2402.18133
• 代码/Code: None

QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction

• 论文/Paper: http://arxiv.org/pdf/2402.17951
• 代码/Code: None

Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

• 论文/Paper: http://arxiv.org/pdf/2402.19479
• 代码/Code: None

SeMoLi: What Moves Together Belongs Together

• 论文/Paper: http://arxiv.org/pdf/2402.19463
• 代码/Code: None

Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction

• 论文/Paper: http://arxiv.org/pdf/2402.19326
• 代码/Code: None

CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition

• 论文/Paper: http://arxiv.org/pdf/2402.19231
• 代码/Code: https://github.com/lu-feng/cricavpr

MemoNav: Working Memory Model for Visual Navigation

• 论文/Paper: http://arxiv.org/pdf/2402.19161
• 代码/Code: None

VideoMAC: Video Masked Autoencoders Meet ConvNets

• 论文/Paper: http://arxiv.org/pdf/2402.19082
• 代码/Code: https://github.com/nust-machine-intelligence-laboratory/videomac

Theoretically Achieving Continuous Representation of Oriented Bounding Boxes

• 论文/Paper: http://arxiv.org/pdf/2402.18975
• 代码/Code: https://github.com/Jittor/JDet

OHTA: One-shot Hand Avatar via Data-driven Implicit Priors

• 论文/Paper: http://arxiv.org/pdf/2402.18969
• 代码/Code: None

WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts

• 论文/Paper: http://arxiv.org/pdf/2402.18956
• 代码/Code: None

Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation

• 论文/Paper: http://arxiv.org/pdf/2402.18920
• 代码/Code: None

SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting

• 论文/Paper: http://arxiv.org/pdf/2402.18848
• 代码/Code: None

ViewFusion: Towards Multi-View Consistency via Interpolated Denoising

• 论文/Paper: http://arxiv.org/pdf/2402.18842
• 代码/Code: None

OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognition

• 论文/Paper: http://arxiv.org/pdf/2402.18786
• 代码/Code: None

NARUTO: Neural Active Reconstruction from Uncertain Target Observations

• 论文/Paper: http://arxiv.org/pdf/2402.18771
• 代码/Code: None

Towards Generalizable Tumor Synthesis

• 论文/Paper: http://arxiv.org/pdf/2402.19470
• 代码/Code: None

Rethinking Multi-domain Generalization with A General Learning Objective

• 论文/Paper: http://arxiv.org/pdf/2402.18853
• 代码/Code: None

Rethinking Inductive Biases for Surface Normal Estimation

• 论文/Paper: http://arxiv.org/pdf/2403.00712
• 代码/Code: https://github.com/baegwangbin/DSINE

SURE: SUrvey REcipes for building reliable and robust deep networks

• 论文/Paper: http://arxiv.org/pdf/2403.00543
• 代码/Code: https://github.com/YutingLi0606/SURE

Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching

• 论文/Paper: http://arxiv.org/pdf/2403.00486
• 代码/Code: https://github.com/Windsrain/Selective-Stereo.

Deformable One-shot Face Stylization via DINO Semantic Guidance

• 论文/Paper: http://arxiv.org/pdf/2403.00459
• 代码/Code: https://github.com/zichongc/DoesFS

CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation

• 论文/Paper: http://arxiv.org/pdf/2403.00274
• 代码/Code: None

NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors

• 论文/Paper: http://arxiv.org/pdf/2403.03122
• 代码/Code: None

Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos

• 论文/Paper: http://arxiv.org/pdf/2403.02782
• 代码/Code: None

HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes

• 论文/Paper: http://arxiv.org/pdf/2403.02769
• 代码/Code: None

Learning Group Activity Features Through Person Attribute Prediction

• 论文/Paper: http://arxiv.org/pdf/2403.02753
• 代码/Code: https://github.com/chihina/GAFL-CVPR2024.

Interactive Continual Learning: Fast and Slow Thinking

• 论文/Paper: http://arxiv.org/pdf/2403.02628
• 代码/Code: None

NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors

• 论文/Paper: http://arxiv.org/pdf/2403.03122
• 代码/Code: None

Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos

• 论文/Paper: http://arxiv.org/pdf/2403.02782
• 代码/Code: None

HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes

• 论文/Paper: http://arxiv.org/pdf/2403.02769
• 代码/Code: None

Learning Group Activity Features Through Person Attribute Prediction

• 论文/Paper: http://arxiv.org/pdf/2403.02753
• 代码/Code: https://github.com/chihina/GAFL-CVPR2024.

Interactive Continual Learning: Fast and Slow Thinking

• 论文/Paper: http://arxiv.org/pdf/2403.02628
• 代码/Code: None

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation

• 论文/Paper: http://arxiv.org/pdf/2403.03890
• 代码/Code: None

DART: Implicit Doppler Tomography for Radar Novel View Synthesis

• 论文/Paper: http://arxiv.org/pdf/2403.03896
• 代码/Code: None

MeaCap: Memory-Augmented Zero-shot Image Captioning

• 论文/Paper: http://arxiv.org/pdf/2403.03715
• 代码/Code: https://github.com/joeyz0z/MeaCap

HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations

• 论文/Paper: http://arxiv.org/pdf/2403.03561
• 代码/Code: None

Continual Segmentation with Disentangled Objectness Learning and Class Recognition

• 论文/Paper: http://arxiv.org/pdf/2403.03477
• 代码/Code: https://github.com/jordangong/CoMasTRe

HDRFlow: Real-Time HDR Video Reconstruction with Large Motions

• 论文/Paper: http://arxiv.org/pdf/2403.03447
• 代码/Code: None

LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

• 论文/Paper: http://arxiv.org/pdf/2403.03421
• 代码/Code: https://github.com/ispc-lab/lead

F$^3$Loc: Fusion and Filtering for Floorplan Localization

• 论文/Paper: http://arxiv.org/pdf/2403.03370
• 代码/Code: None

Enhancing Vision-Language Pre-training with Rich Supervisions

• 论文/Paper: http://arxiv.org/pdf/2403.03346
• 代码/Code: None

Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed

• 论文/Paper: http://arxiv.org/pdf/2403.04765
• 代码/Code: None

Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning

• 论文/Paper: http://arxiv.org/pdf/2403.04492
• 代码/Code: https://github.com/rashindrie/dipa

Learning to Remove Wrinkled Transparent Film with Polarized Prior

• 论文/Paper: http://arxiv.org/pdf/2403.04368
• 代码/Code: https://github.com/jqtangust/filmremoval

LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking

• 论文/Paper: http://arxiv.org/pdf/2403.04303
• 代码/Code: None

Active Generalized Category Discovery

• 论文/Paper: http://arxiv.org/pdf/2403.04272
• 代码/Code: https://github.com/mashijie1028/activegcd

MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection

• 论文/Paper: http://arxiv.org/pdf/2403.04149
• 代码/Code: https://github.com/ispc-lab/map

A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition

• 论文/Paper: http://arxiv.org/pdf/2403.04245
• 代码/Code: https://github.com/dalision/modalbiasavsr

Seamless Human Motion Composition with Blended Positional Encodings

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

DiffusionLight: Light Probes for Free by Painting a Chrome Ball

• 论文/Paper: https://arxiv.org/abs/2312.09168
• 代码/Code:https://github.com/DiffusionLight/DiffusionLight

SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting

• 论文/Paper: http://arxiv.org/pdf/2403.05087
• 代码/Code: https://github.com/initialneil/SplattingAvatar

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation

• 论文/Paper: http://arxiv.org/pdf/2403.06946
• 代码/Code: https://github.com/tl-uestc/unimos

Real-Time Simulated Avatar from Head-Mounted Sensors

• 论文/Paper: http://arxiv.org/pdf/2403.06862
• 代码/Code: None

DiaLoc: An Iterative Approach to Embodied Dialog Localization

• 论文/Paper: http://arxiv.org/pdf/2403.06846
• 代码/Code: None

FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation

• 论文/Paper: http://arxiv.org/pdf/2403.06775
• 代码/Code: https://github.com/modelscope/facechain

EarthLoc: Astronaut Photography Localization by Indexing Earth from Space

• 论文/Paper: http://arxiv.org/pdf/2403.06758
• 代码/Code: https://github.com/gmberton/earthloc

CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective

• 论文/Paper: http://arxiv.org/pdf/2403.06676
• 代码/Code: https://github.com/snskysk/cam-back-again

Distributionally Generative Augmentation for Fair Facial Attribute Classification

• 论文/Paper: http://arxiv.org/pdf/2403.06606
• 代码/Code: https://github.com/heqianpei/diga

Exploiting Style Latent Flows for Generalizing Deepfake Detection Video Detection

• 论文/Paper: http://arxiv.org/pdf/2403.06592
• 代码/Code: None

MoST: Motion Style Transformer between Diverse Action Contents

• 论文/Paper: http://arxiv.org/pdf/2403.06225
• 代码/Code: https://github.com/Boeun-Kim/MoST.

Coherent Temporal Synthesis for Incremental Action Segmentation

• 论文/Paper: http://arxiv.org/pdf/2403.06102
• 代码/Code: None

Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?

• 论文/Paper: http://arxiv.org/pdf/2403.06092
• 代码/Code: None

LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content

• 论文/Paper: http://arxiv.org/pdf/2403.05854
• 代码/Code: None

PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor

• 论文/Paper: http://arxiv.org/pdf/2403.06668
• 代码/Code: None

SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection

• 论文/Paper: http://arxiv.org/pdf/2403.03170
• 代码/Code: None

Multi-Task Dense Prediction via Mixture of Low-Rank Experts

• 论文/Paper: https://arxiv.org/abs/2403.17749
• 代码/Code: https://github.com/YuqiYang213/MLoRE

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension

• 论文/Paper: http://arxiv.org/pdf/2403.07874
• 代码/Code: https://github.com/zh460045050/v2l-tokenizer

Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis

• 论文/Paper: http://arxiv.org/pdf/2403.07719
• 代码/Code: https://github.com/wonderlandxd/wikg

Robust Synthetic-to-Real Transfer for Stereo Matching

• 论文/Paper: http://arxiv.org/pdf/2403.07705
• 代码/Code: https://github.com/jiaw-z/dkt-stereo

CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers

• 论文/Paper: http://arxiv.org/pdf/2403.07700
• 代码/Code: https://github.com/shahaf-arica/cuvler

Masked AutoDecoder is Effective Multi-Task Vision Generalist

• 论文/Paper: http://arxiv.org/pdf/2403.07692
• 代码/Code: https://github.com/hanqiu-hq/mad

PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution

• 论文/Paper: http://arxiv.org/pdf/2403.07589
• 代码/Code: None

Unleashing Network Potentials for Semantic Scene Completion

• 论文/Paper: http://arxiv.org/pdf/2403.07560
• 代码/Code: https://github.com/fereenwong/ammnet

Open-World Semantic Segmentation Including Class Similarity

• 论文/Paper: http://arxiv.org/pdf/2403.07532
• 代码/Code: https://github.com/PRBonn/ContMAV

ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions

• 论文/Paper: http://arxiv.org/pdf/2403.07392
• 代码/Code: https://github.com/Traffic-X/ViT-CoMer

FSC: Few-point Shape Completion

• 论文/Paper: http://arxiv.org/pdf/2403.07359
• 代码/Code: None

Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture

• 论文/Paper: http://arxiv.org/pdf/2403.07347
• 代码/Code: https://github.com/jiafei127/fd4mm

A Bayesian Approach to OOD Robustness in Image Classification

• 论文/Paper: http://arxiv.org/pdf/2403.07277
• 代码/Code: None

返回目录/back