LISO: LiDAR-Only Self-Supervised 3D Object Detection

Abstract

3D object detection is one of the most important components in any Self-Driving stack, but current object detectors require costly & slow manual annotation of 3D bounding boxes to perform well. Recently, several methods emerged to generate without human supervision, however, all of these methods have various drawbacks: Some methods require sensor rigs with full camera coverage and accurate calibration, partly supplemented by an auxiliary optical flow engine. Others require expensive high-precision localization to find objects that disappeared over multiple drives. We introduce a novel self-supervised method to train object detection networks, requiring only unlabeled sequences of lidar point clouds. We call this trajectory-regularized self-training. It utilizes a self-supervised network under the hood to generate, track, and iteratively refine . We demonstrate the effectiveness of our approach for multiple object detection networks across multiple real-world datasets. Code will be released1 . 1 https://github.com/baurst/liso