COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

arXiv:2312.01919v2 Announce Type: replace
Abstract: The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabilities. To achieve this, current works try to construct a Tri-Perspective View (TPV) or Occupancy (OCC) representation extending from the Bird-Eye-View perception. However, compressed views like TPV representation lose 3D geometry information while raw and sparse OCC representation requires heavy but redundant computational costs. To address the above limitations, we propose Compact Occupancy …

abstract arxiv autonomous autonomous driving bird capabilities community compact construct cs.cv current driving general however object perception perspective prediction recognition representation transformer type view vision