Scene Understanding

Emergent Outlier View Rejection in Visual Geometry Grounded Transformers CVPR 2026 Event-Guided Scene Text Image Super-Resolution AAAI 2026 Fine-Grained Representation for Lane Topology Reasoning AAAI 2026 FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning CVPR 2026 Fusion of Depth and Semantics for Probabilistic Floorplan Localization CVPR 2026 G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning CVPR 2026 GAEA: A Geolocation Aware Conversational Assistant WACV 2026 Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction CVPR 2026 GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation CVPR 2026 Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction CVPR 2026 GenMatter: Perceiving Physical Objects with Generative Matter Models CVPR 2026 Geometry-Aware Cross-Modal Graph Alignment for Referring Segmentation in 3D Gaussian Splatting CVPR 2026 GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry CVPR 2026 GeoX-Bench: Benchmarking Cross-View Geo-Localization and Pose Estimation Capabilities of Large Multimodal Models AAAI 2026 Grounded Chain-of-Thought for Multimodal Large Language Models CVPR 2026 Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian Splatting CVPR 2026 HOLO: Holistic Lightweight Optimization for Scene Understanding with Auto-Annotation and Multimodal Learning WACV 2026 HyperD: Hybrid Periodicity Decoupling Framework for Traffic Forecasting AAAI 2026 Inferring Compositional 4D Scenes without Ever Seeing One CVPR 2026 Isolating the Role of Temporal Information in Video Saliency: A Controlled Experimental Analysis WACV 2026 LangField4D: Learning Identity-Adaptive and Spatio-Temporal Continuous 4D Language Fields for Dynamic Scenes CVPR 2026 Layout Anything: One Transformer for Universal Room Layout Estimation WACV 2026 Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images CVPR 2026 Learning Spatial-Temporal Consistency for 3D Semantic Scene Completion CVPR 2026 Lifting Unlabeled Internet-level Data for 3D Scene Understanding CVPR 2026