Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction

arXiv:2307.09555v2 Announce Type: replace
Abstract: Neural radiance fields (NeRFs) have become a ubiquitous tool for modeling scene appearance and geometry from multiview imagery. Recent work has also begun to explore how to use additional supervision from lidar or depth sensor measurements in the NeRF framework. However, previous lidar-supervised NeRFs focus on rendering conventional camera imagery and use lidar-derived point cloud data as auxiliary supervision; thus, they fail to incorporate the underlying image formation model of the lidar. Here, we propose …

3d reconstruction abstract arxiv become begun cs.cv eess.iv explore fields framework geometry however lidar modeling nerf neural radiance fields sensor supervision synthesis tool type view work