Scene Understanding

PlaneRAS: Learning Planar Primitives for 3D Plane Recovery ICCV 2025 Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation AAAI 2025 Proactive Scene Decomposition and Reconstruction ICCV 2025 Probing the Mid-level Vision Capabilities of Self-Supervised Learning CVPR 2025 ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering EMNLP 2025 Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting ICML 2025 PseudoMapTrainer: Learning Online Mapping without HD Maps ICCV 2025 PVMamba: Parallelizing Vision Mamba via Dynamic State Aggregation ICCV 2025 RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning AAAI 2025 RAV: Retrieval-Augmented Voting for Tactile Descriptions Without Training EMNLP 2025 RayZer: A Self-supervised Large View Synthesis Model ICCV 2025 Reasoning Mamba: Hypergraph-Guided Region Relation Calculating for Weakly Supervised Affordance Grounding CVPR 2025 Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions CVPR 2025 Reconstructing People, Places, and Cameras CVPR 2025 Recurrence-Based Vanishing Point Detection WACV 2025 Referring Expressions as a Lens into Spatial Language Grounding in Vision-Language Models IJCNLP 2025 Region-aware Difference Distilling with Attribute-guided Contrastive Regularization for Change Captioning AAAI 2025 REGNav: Room Expert Guided Image-Goal Navigation AAAI 2025 RelationField: Relate Anything in Radiance Fields CVPR 2025 Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization CVPR 2025 Robust Adverse Weather Removal via Spectral-based Spatial Grouping ICCV 2025 Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction ICCV 2025 ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting CVPR 2025 RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation CVPR 2025 R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization CVPR 2025