Scene Understanding

3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding CVPR 2026 3D-IDE: 3D Implicit Depth Emergent CVPR 2026 A Brain-Inspired Saliency Prediction Framework for Human-AI Cognitive Consistency in AIGC Content via Multi-Region Liquid Neurons AAAI 2026 Active3D: Active High-Fidelity 3D Reconstruction via Multi-Level Uncertainty Quantification AAAI 2026 AirSim360: A Panoramic Simulation Platform within Drone View CVPR 2026 ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild CVPR 2026 AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Construction WACV 2026 AV-SSAN: Audio-Visual Selective DOA Estimation Through Explicit Multi-Band Semantic-Spatial Alignment AAAI 2026 Beyond Quadratic: Linear-Time Change Detection with RWKV AAAI 2026 BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection CVPR 2026 Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching CVPR 2026 CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models ACL 2026 CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition WACV 2026 CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments ACL 2026 Complet4R: Geometric Complete 4D Reconstruction CVPR 2026 Computer Vision Modeling of the Development of Geometric and Numerical Concepts in Humans AAAI 2026 Consistent Instance Field for Dynamic Scene Understanding CVPR 2026 Curvature-Aware Captioning: Leveraging Geodesic Attention for 3D Scene Understanding CVPR 2026 CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning WACV 2026 Debiased Multiplex Tokenizer for Efficient Map-Free Visual Relocalization AAAI 2026 Detecting Social Engagement of Elderly From Lifelog Image-streams to Identify Effective Cues for Autobiographic Recall WACV 2026 DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime CVPR 2026 Dynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos CVPR 2026 Dynamic Visual SLAM using a General 3D Prior CVPR 2026 EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding CVPR 2026