AI RESEARCH

LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields

arXiv CS.CV

ArXi:2605.15496v1 Announce Type: cross Neural distance fields offer a compact and continuous representation of 3D geometry, making them attractive for incremental LiDAR mapping. However, their online optimization is vulnerable to catastrophic forgetting, where new observations can degrade previously reconstructed geometry. Replay-based