Computer Vision

Reducing the Content Bias for AI-Generated Image Detection WACV 2025 RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions ICCV 2025 Region-Level Data Attribution for Text-to-Image Generative Models ICCV 2025 REGNav: Room Expert Guided Image-Goal Navigation AAAI 2025 Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes ICCV 2025 Relaxed Rotational Equivariance via G-Biases in Vision AAAI 2025 ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters AAAI 2025 Rethinking Personalized Aesthetics Assessment: Employing Physique Aesthetics Assessment as An Exemplification CVPR 2025 Retrieving Argument Graphs Using Vision Transformers ACL 2025 RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors ICCV 2025 Risk Controlled Image Retrieval AAAI 2025 RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression CVPR 2025 RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics CVPR 2025 Robotic Visual Instruction CVPR 2025 RSTSIC: Reparameterized Swin Transformer Stereo Image Compression ACML 2025 RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges CVPR 2025 S2D-LFE: Sparse-to-Dense Light Field Event Generation CVPR 2025 SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers ICCV 2025 SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree ICCV 2025 SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures ICCV 2025 SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE CVPR 2025 SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers CVPR 2025 SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection AAAI 2025 SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation ICCV 2025 ScrewSplat: An End-to-End Method for Articulated Object Recognition CoRL 2025