OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries

arXiv:2312.03774v3 Announce Type: replace
Abstract: Occupancy prediction has increasingly garnered attention in recent years for its fine-grained understanding of 3D scenes. Traditional approaches typically rely on dense, regular grid representations, which often leads to excessive computational demands and a loss of spatial details for small objects. This paper introduces OctreeOcc, an innovative 3D occupancy prediction framework that leverages the octree representation to adaptively capture valuable information in 3D, offering variable granularity to accommodate object shapes and semantic regions of varying …

3d scenes abstract arxiv attention computational cs.cv fine-grained grid leads loss objects paper prediction queries small spatial type understanding