Scene Understanding

TopicGeo: An Efficient Unified Framework for Geolocation ICCV 2025 Towards Generalizable Scene Change Detection CVPR 2025 Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method CVPR 2025 Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Method CVPR 2025 Towards Smart Point-and-Shoot Photography CVPR 2025 Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation CVPR 2025 TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes WACV 2025 Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing ICCV 2025 Transparent Vision: A Theory of Hierarchical Invariant Representations ICCV 2025 Trial-Oriented Visual Rearrangement ICCV 2025 TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring ICCV 2025 TSC-Net: Prediction of Pedestrian Trajectories by Trajectory-Scene-Cell Classification ICLR 2025 UAVScenes: A Multi-Modal Dataset for UAVs ICCV 2025 uLayout: Unified Room Layout Estimation for Perspective and Panoramic Images WACV 2025 Understanding Matters: Semantic-Structural Determined Visual Relocalization for Large Scenes IJCAI 2025 Underwater Visual SLAM with Depth Uncertainty and Medium Modeling ICCV 2025 Unified Reconstruction of Static and Dynamic Scenes from Events CVPR 2025 Universal Scene Graph Generation CVPR 2025 Unsupervised Single-Image Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training WACV 2025 UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios AAAI 2025 UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction WACV 2025 V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction ICCV 2025 VCD: A Dataset for Visual Commonsense Discovery in Images ACL 2025 Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval CVPR 2025 VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regions ICCV 2025