OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments

arXiv:2312.09243v2 Announce Type: replace
Abstract: As a fundamental task of vision-based perception, 3D occupancy prediction reconstructs 3D structures of surrounding environments. It provides detailed information for autonomous driving planning and navigation. However, most existing methods heavily rely on the LiDAR point clouds to generate occupancy ground truth, which is not available in the vision-based system. In this paper, we propose an OccNeRF method for training occupancy networks without 3D supervision. Different from previous works which consider a bounded scene, we …

abstract arxiv autonomous autonomous driving cs.cv driving environments free generate however information lidar navigation perception planning prediction truth type vision