MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection

arXiv:2404.04910v1 Announce Type: new
Abstract: Monocular 3D object detection (Mono3D) is an indispensable research topic in autonomous driving, thanks to the cost-effective monocular camera sensors and its wide range of applications. Since the image perspective has depth ambiguity, the challenges of Mono3D lie in understanding 3D scene geometry and reconstructing 3D object information from a single image. Previous methods attempted to transfer 3D information directly from the LiDAR-based teacher to the camera-based student. However, a considerable gap in feature representation …

3d object 3d object detection abstract applications arxiv assistant autonomous autonomous driving challenges cost cs.cv detection distillation driving geometry image knowledge object perspective research scene geometry sensors teaching teaching assistant type understanding