Unified Spatio-Temporal Tri-Perspective View Representation for 3D Semantic Occupancy Prediction

arXiv:2401.13785v2 Announce Type: replace
Abstract: Holistic understanding and reasoning in 3D scenes play a vital role in the success of autonomous driving systems. The evolution of 3D semantic occupancy prediction as a pretraining task for autonomous driving and robotic downstream tasks capture finer 3D details compared to methods like 3D detection. Existing approaches predominantly focus on spatial cues such as tri-perspective view embeddings (TPV), often overlooking temporal cues. This study introduces a spatiotemporal transformer architecture S2TPVFormer for temporally coherent 3D …

3d scenes abstract arxiv autonomous autonomous driving autonomous driving systems cs.cv driving evolution perspective prediction pretraining reasoning representation robotic role semantic success systems tasks temporal type understanding view vital