Abstract: Giving machines the ability to infer the complete 3D geometry and semantics of complex scenes is crucial for many downstream tasks, such as decision-making and planning. Vision-centric ...

Abstract: Recently, 3D multi-object tracking (MOT) has widely adopted the standard tracking-by-detection paradigm, which solves the association problem between detections and tracks. Many ...

Official code for the CVPR 2026 paper: Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation Kailing Li, Tianwen Qian, Lijin Yang, Yuqian Fu, Jingyu Gong, ...

We propose WorldStereo, a novel framework that bridges camera-guided video generation and 3D reconstruction via two dedicated geometric memory modules: Global-Geometric Memory (GGM) enables precise ...