Manual-Label Free 3D Detection via An Open-Source Simulator

TL;DR

This paper introduces a novel method for 3D object detection using LiDAR data that eliminates the need for manual labels by leveraging synthetic data from a simulator and domain adaptation techniques.

Contribution

It presents a new domain adaptive VoxelNet that trains on synthetic data and adapts to real-world data, reducing labeling costs.

Findings

Achieves 76.66% mAP on KITTI BEV mode

Achieves 56.64% mAP on KITTI 3D mode

Demonstrates effective training without manual labels

Abstract

LiDAR based 3D object detectors typically need a large amount of detailed-labeled point cloud data for training, but these detailed labels are commonly expensive to acquire. In this paper, we propose a manual-label free 3D detection algorithm that leverages the CARLA simulator to generate a large amount of self-labeled training samples and introduces a novel Domain Adaptive VoxelNet (DA-VoxelNet) that can cross the distribution gap from the synthetic data to the real scenario. The self-labeled training samples are generated by a set of high quality 3D models embedded in a CARLA simulator and a proposed LiDAR-guided sampling algorithm. Then a DA-VoxelNet that integrates both a sample-level DA module and an anchor-level DA module is proposed to enable the detector trained by the synthetic data to adapt to real scenario. Experimental results show that the proposed unsupervised DA 3D detector on KITTI evaluation set can achieve 76.66% and 56.64% mAP on BEV mode and 3D mode respectively. The results reveal a promising perspective of training a LIDAR-based 3D detector without any hand-tagged label.