Scene Understanding

LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds CVPR 2026 MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping CVPR 2026 Matching Semantically Similar Non-Identical Objects WACV 2026 Memory-Augmented Scene Understanding and Exploration for Open-World Aerial Object-Goal Navigation CVPR 2026 MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes AAAI 2026 Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis CVPR 2026 Mixture-of-Experts based Feature Decoupling for Open Vocabulary Scene Graph Generation CVPR 2026 Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes CVPR 2026 MORE-STEM: Long-Short MemOry REcall and Spatio-TEmporal Consistency Model for Query-Driven 3D/4D Point Cloud Segmentation CVPR 2026 MOSAIC-GS: Monocular Scene Reconstruction via Advanced Initialization for Complex Dynamic Environments CVPR 2026 MRGeo: Robust Cross-View Geo-Localization of Corrupted Images via Spatial and Channel Feature Enhancement AAAI 2026 Multi-modal Frequency Decomposition Network for Semantic Scene Completion CVPR 2026 NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction WACV 2026 NeuroRule: Bridging Vision and Logic with Differentiable Rule Induction CVPR 2026 Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs CVPR 2026 OccAny: Generalized Unconstrained Urban 3D Occupancy CVPR 2026 Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning WACV 2026 One2Seq: One-Token Wise Decoder for Efficient Scene Text Recognition AAAI 2026 OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting CVPR 2026 OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding AAAI 2026 OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding CVPR 2026 OptiMVMap: Offline Vectorized Map Construction via Optimal Multi-vehicle Perspectives CVPR 2026 PALMS+: Modular Image-Based Floor Plan Localization Leveraging Depth Foundation Model WACV 2026 PatchScene: Patch-based Voxel Diffusion Model for Large-Scale Scene Completion CVPR 2026 Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching WACV 2026