UniLiDAR: Bridge the domain gap among different LiDARs for continual learning

arXiv:2403.08512v1 Announce Type: new
Abstract: LiDAR-based 3D perception algorithms have evolved rapidly alongside the emergence of large datasets. Nonetheless, considerable performance degradation often ensues when models trained on a specific dataset are applied to other datasets or real-world scenarios with different LiDAR. This paper aims to develop a unified model capable of handling different LiDARs, enabling continual learning across diverse LiDAR datasets and seamless deployment across heterogeneous platforms. We observe that the gaps among datasets primarily manifest in geometric disparities …

abstract algorithms arxiv bridge continual cs.cv dataset datasets domain emergence gap large datasets lidar paper perception performance type world