VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection

arXiv:2404.00149v1 Announce Type: new
Abstract: Monocular 3D object detection poses a significant challenge in 3D scene understanding due to its inherently ill-posed nature in monocular depth estimation. Existing methods heavily rely on supervised learning using abundant 3D labels, typically obtained through expensive and labor-intensive annotation on LiDAR point clouds. To tackle this problem, we propose a novel weakly supervised 3D object detection framework named VSRD (Volumetric Silhouette Rendering for Detection) to train 3D object detectors without any 3D supervision but …

3d object 3d object detection arxiv cs.cv detection instance object rendering type