Commonsense Prototype for Outdoor Unsupervised 3D Object Detection

TL;DR

This paper introduces a Commonsense Prototype-based Detector (CPD) for unsupervised 3D object detection that improves accuracy by leveraging high-quality bounding box prototypes and geometric knowledge, significantly outperforming existing methods.

Contribution

The paper proposes a novel CPD method that constructs commonsense prototypes to refine pseudo-labels and enhance detection accuracy in sparse LiDAR scans, advancing unsupervised 3D detection.

Findings

CPD outperforms state-of-the-art unsupervised detectors on multiple datasets.

CPD achieves near fully supervised detection performance on KITTI.

The code for CPD will be publicly available.

Abstract

The prevalent approaches of unsupervised 3D object detection follow cluster-based pseudo-label generation and iterative self-training processes. However, the challenge arises due to the sparsity of LiDAR scans, which leads to pseudo-labels with erroneous size and position, resulting in subpar detection performance. To tackle this problem, this paper introduces a Commonsense Prototype-based Detector, termed CPD, for unsupervised 3D object detection. CPD first constructs Commonsense Prototype (CProto) characterized by high-quality bounding box and dense points, based on commonsense intuition. Subsequently, CPD refines the low-quality pseudo-labels by leveraging the size prior from CProto. Furthermore, CPD enhances the detection accuracy of sparsely scanned objects by the geometric knowledge from CProto. CPD outperforms state-of-the-art unsupervised 3D detectors on Waymo Open Dataset (WOD), PandaSet, and KITTI datasets by a large margin. Besides, by training CPD on WOD and testing on KITTI, CPD attains 90.85% and 81.01% 3D Average Precision on easy and moderate car classes, respectively. These achievements position CPD in close proximity to fully supervised detectors, highlighting the significance of our method. The code will be available at https://github.com/hailanyi/CPD.