Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?

arXiv:2403.02818v1 Announce Type: new
Abstract: Current state-of-the-art (SOTA) 3D object detection methods often require a large amount of 3D bounding box annotations for training. However, collecting such large-scale densely-supervised datasets is notoriously costly. To reduce the cumbersome data annotation process, we propose a novel sparsely-annotated framework, in which we just annotate one 3D object per scene. Such a sparse annotation strategy could significantly reduce the heavy annotation burden, while inexact and incomplete sparse supervision may severely deteriorate the detection performance. …

3d object 3d object detection arxiv cloud cs.cv detection labels object type