Conferences · eligible papers
CVPR
2021–2025 確定版
2025 · 2,871 papers
このEditionに反映済みのmain full research papersのみ掲載しています。著者リンクは日本の大学への著者別所属根拠がある場合に限ります。
- RelationField: Relate Anything in Radiance Fields
日本大学: 関与なし(対象大学)
- Relative Pose Estimation through Affine Corrections of Monocular Depth Priors
日本大学: 関与なし(対象大学)
- Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization
日本大学: 関与なし(対象大学)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios
日本大学: 関与なし(対象大学)
- Removing Reflections from RAW Photos
日本大学: 関与なし(対象大学)
- Reproducible Vision-Language Models Meet Concepts Out of Pre-Training
日本大学: 関与なし(対象大学)
- Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation
日本大学: 関与なし(対象大学)
- Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation
日本大学: 関与なし(対象大学)
- ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
日本大学: 関与なし(対象大学)
- Resilient Sensor Fusion Under Adverse Sensor Failures via Multi-Modal Expert Fusion
日本大学: 関与なし(対象大学)
- RestorGS: Depth-aware Gaussian Splatting for Efficient 3D Scene Restoration
日本大学: 関与なし(対象大学)
- Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation
日本大学: 関与なし(対象大学)
- Rethinking Correspondence-based Category-Level Object Pose Estimation
日本大学: 関与なし(対象大学)
- Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention
日本大学: 関与なし(対象大学)
- Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression
日本大学: 関与なし(対象大学)
- Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting
日本大学: 関与なし(対象大学)
- Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach
日本大学: 関与なし(対象大学)
- Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages
日本大学: 関与なし(対象大学)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection
日本大学: 関与なし(対象大学)
- Rethinking Noisy Video-Text Retrieval via Relation-aware Alignment
日本大学: 関与なし(対象大学)
- Rethinking Personalized Aesthetics Assessment: Employing Physique Aesthetics Assessment as An Exemplification
日本大学: 関与なし(対象大学)
- Rethinking Query-based Transformer for Continual Image Segmentation
日本大学: 関与なし(対象大学)
- Rethinking Reconstruction and Denoising in the Dark: New Perspective, General Architecture and Beyond
日本大学: 関与なし(対象大学)
- Rethinking Spiking Self-Attention Mechanism: Implementing a-XNOR Similarity Calculation in Spiking Transformers
日本大学: 関与なし(対象大学)
- Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction
日本大学: 関与なし(対象大学)
- Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks
日本大学: 関与なし(対象大学)
- Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion
日本大学: 関与なし(対象大学)
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector
日本大学: 関与なし(対象大学)
- Rethinking the Adversarial Robustness of Multi-Exit Neural Networks in an Attack-Defense Game
日本大学: 関与なし(対象大学)
- Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
日本大学: 関与なし(対象大学)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
日本大学: 関与なし(対象大学)
- Reversible Decoupling Network for Single Image Reflection Removal
日本大学: 関与なし(対象大学)
- Reversing Flow for Image Restoration
日本大学: 関与なし(対象大学)
- Revisiting Audio-Visual Segmentation with Vision-Centric Transformer
日本大学: 関与なし(対象大学)
- Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
日本大学: 関与なし(対象大学)
- Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction
日本大学: 関与なし(対象大学)
- Revisiting Generative Replay for Class Incremental Object Detection
日本大学: 関与なし(対象大学)
- Revisiting MAE Pre-training for 3D Medical Image Segmentation
日本大学: 関与なし(対象大学)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety
日本大学: 関与なし(対象大学)
- Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward
日本大学: 関与なし(対象大学)
- RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos
日本大学: 関与なし(対象大学)
- RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety
日本大学: 関与なし(対象大学)
- RivuletMLP: An MLP-based Architecture for Efficient Compressed Video Quality Enhancement
日本大学: 関与なし(対象大学)
- RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images
日本大学: 関与なし(対象大学)
- RoadSocial: A Diverse VideoQA Dataset and Benchmark for Road Event Understanding from Social Video Narratives
日本大学: 関与なし(対象大学)
- RobSense: A Robust Multi-modal Foundation Model for Remote Sensing with Static, Temporal, and Incomplete Data Adaptability
日本大学: 関与なし(対象大学)
- RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete
日本大学: 関与なし(対象大学)
- RoboGround: Robotic Manipulation with Grounded Vision-Language Priors
日本大学: 関与なし(対象大学)
- RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training
日本大学: 関与なし(対象大学)
- RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments
日本大学: 関与なし(対象大学)
- RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics
日本大学: 関与なし(対象大学)
- RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins
日本大学: 関与なし(対象大学)
- Robotic Visual Instruction
日本大学: 関与なし(対象大学)
- Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild
日本大学: 関与なし(対象大学)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment
日本大学: 関与なし(対象大学)
- Robust Message Embedding via Attention Flow-Based Steganography
日本大学: 関与なし(対象大学)
- Robust Multi-Object 4D Generation for In-the-wild Videos
日本大学: 関与なし(対象大学)
- Robust Multimodal Survival Prediction with Conditional Latent Differentiation Variational AutoEncoder
日本大学: 関与なし(対象大学)
- Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On
日本大学: 関与なし(対象大学)
- RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing
日本大学: 関与なし(対象大学)
- RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation
日本大学: 関与なし(対象大学)
- Rotation-Equivariant Self-Supervised Method in Image Denoising
日本大学: 関与なし(対象大学)
- S2D-LFE: Sparse-to-Dense Light Field Event Generation
日本大学: 関与なし(対象大学)
- S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting
日本大学: 関与なし(対象大学)
- S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Model with Spatio-Temporal Visual Representation
日本大学: 関与なし(対象大学)
- SACB-Net: Spatial-awareness Convolutions for Medical Image Registration
日本大学: 関与なし(対象大学)
- SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining
日本大学: 関与なし(対象大学)
- SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing
日本大学: 関与なし(対象大学)
- SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
日本大学: 関与なし(対象大学)
- SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost
日本大学: 関与なし(対象大学)
- SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model
日本大学: 関与なし(対象大学)
- SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes
日本大学: 関与なし(対象大学)
- SAM2Object: Consolidating View Consistency via SAM2 for Zero-Shot 3D Instance Segmentation
日本大学: 関与なし(対象大学)
- SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity
日本大学: 関与なし(対象大学)
- SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation
日本大学: 関与なし(対象大学)
- SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE
日本大学: 関与なし(対象大学)
- SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
日本大学: 関与なし(対象大学)
- SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens
日本大学: 関与なし(対象大学)
- SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers
日本大学: 関与なし(対象大学)
- SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
日本大学: 関与なし(対象大学)
- SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow
日本大学: 関与なし(対象大学)
- SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer
日本大学: 関与なし(対象大学)
- SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures
日本大学: 関与なし(対象大学)
- SDBF: Steep-Decision-Boundary Fingerprinting for Hard-Label Tampering Detection of DNN Models
日本大学: 関与なし(対象大学)
- SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction
日本大学: 関与なし(対象大学)
- SEAL: Semantic Attention Learning for Long Video Representation
日本大学: 関与なし(対象大学)
- SEC-Prompt:SEmantic Complementary Prompting for Few-Shot Class-Incremental Learning
日本大学: 関与なし(対象大学)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection
日本大学: 関与なし(対象大学)
- SET: Spectral Enhancement for Tiny Object Detection
日本大学: 関与なし(対象大学)
- SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding
日本大学: 関与なし(対象大学)
- SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
日本大学: 関与なし(対象大学)
- SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view Images
日本大学: 関与なし(対象大学)
- SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection
日本大学: 関与なし(対象大学)
- SGCR: Spherical Gaussians for Efficient 3D Curve Reconstruction
日本大学: 関与なし(対象大学)
- SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion
日本大学: 関与なし(対象大学)
- SGSST: Scaling Gaussian Splatting Style Transfer
日本大学: 関与なし(対象大学)
- SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model
日本大学: 関与なし(対象大学)
- SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
日本大学: 関与なし(対象大学)
- SINR: Sparsity Driven Compressed Implicit Neural Representations
日本大学: 関与なし(対象大学)
- SIR-DIFF: Sparse Image Sets Restoration with Multi-View Diffusion Model
日本大学: 関与なし(対象大学)