Pre-Training LiDAR-Based 3D Object Detectors Through Colorization

arXiv:2310.14592v2 Announce Type: replace-cross
Abstract: Accurate 3D object detection and understanding for self-driving cars heavily relies on LiDAR point clouds, necessitating large amounts of labeled data to train. In this work, we introduce an innovative pre-training approach, Grounded Point Colorization (GPC), to bridge the gap between data and labels by teaching the model to colorize LiDAR point clouds, equipping it with valuable semantic cues. To tackle challenges arising from color variations and selection bias, we incorporate color as "context" by …

3d object 3d object detection abstract arxiv bridge cars colorization cs.cv cs.lg data detection driving gap labels lidar pre-training self-driving teaching through train training type understanding work