Commonsense Prototype for Outdoor Unsupervised 3D Object Detection

Hai Wu, Shijia Zhao, Xun Huang, Chenglu Wen, Xin Li, Cheng Wang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 14968-14977

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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Hai and Zhao, Shijia and Huang, Xun and Wen, Chenglu and Li, Xin and Wang, Cheng}, title = {Commonsense Prototype for Outdoor Unsupervised 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14968-14977} }