3d grounding 1cross-view localization 1geometry transfer 1semantic consistency 1structure learning 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CV2026
More Than Where You Are: Learning Semantics, Structure, and Geometry from Cross-View Localization
Mao Chen, Xiangkai Zhang, Zhiyong Liu +2
The paper introduces CROSS, a cross-view localization framework that uses 3D-grounded alignment, structure-aware matching, and hypothesis ranking to learn stable semantics, reliabl…
cs.CV2026
Globally Localizing Lunar Rover in Pixels via Graph Alignment
Mao Chen, Xu Yang, Chuankai Liu +5
Precise rover localization is a prerequisite for autonomous lunar exploration, yet the absence of Global Navigation Satellite System (GNSS) signals and the cumulative drift of loca…
cs.RO2026
Semantic Evidence Regulation via Relational Bias for Zero-Shot Object Navigation
Weitao An, Chenghao Xu, Xu Yang +1
Object navigation requires an embodied agent to locate a target object in an unknown environment through visual observations. Existing zero-shot methods typically leverage open-voc…