Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection

arXiv:2107.13931v2 Announce Type: replace
Abstract: As a crucial task of autonomous driving, 3D object detection has made great progress in recent years. However, monocular 3D object detection remains a challenging problem due to the unsatisfactory performance in depth estimation. Most existing monocular methods typically directly regress the scene depth while ignoring important relationships between the depth and various geometric elements (e.g. bounding box sizes, 3D object dimensions, and object poses). In this paper, we propose to learn geometry-guided depth estimation …

3d object 3d object detection arxiv cs.cv detection geometry modeling object type via