Search papers, labs, and topics across Lattice.
3
0
5
4
Fusing semantic and geometric cues yields more robust and discriminative local features, outperforming methods relying on single appearance cues.
LiDAR place recognition gets a serious boost from a novel BEV encoding that captures fine-grained geometric structure, outperforming existing methods in complex environments while maintaining real-time performance.
Imagine pinpointing your location in a city using only a text description and OpenStreetMap data – this paper makes that a reality with a new benchmark and method that significantly outperforms existing localization techniques.
