Scene Understanding

FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction CVPR 2025 From Coarse to Fine: A Matching and Alignment Framework for Unsupervised Cross-View Geo-Localization AAAI 2025 From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding ACL 2025 FROSS: Faster-Than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images ICCV 2025 Game4Loc: A UAV Geo-Localization Benchmark from Game Data AAAI 2025 GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation CVPR 2025 Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders CVPR 2025 GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks ICCV 2025 GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder EMNLP 2025 GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning ACL 2025 GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing CVPR 2025 GlyphPattern: An Abstract Pattern Recognition for Vision-Language Models ACL 2025 GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models ICCV 2025 GraphAD: Interaction Scene Graph for End-to-end Autonomous Driving IJCAI 2025 Graph-based Document Structure Analysis ICLR 2025 Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting ICLR 2025 GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space ICCV 2025 Hierarchical 3D Scene Graphs Construction Outdoors ICCV 2025 HOMO-Feature: Cross-Arbitrary-Modal Image Matching with Homomorphism of Organized Major Orientation ICCV 2025 HomoMatcher: Achieving Dense Feature Matching with Semi-Dense Efficiency by Homography Estimation AAAI 2025 Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes CVPR 2025 HORP: Human-Object Relation Priors Guided HOI Detection CVPR 2025 HouseTour: A Virtual Real Estate A(I)gent ICCV 2025 How Would It Sound? Material-Controlled Multimodal Acoustic Profile Generation for Indoor Scenes ICCV 2025 HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding? ICCV 2025