Unsupervised 3D Object Detection Using Commonsense Prototypes

This paper introduces a Commonsense Prototype-based Detector (CPD) that can perform accurate unsupervised 3D object detection without human annotations. CPD constructs high-quality commonsense prototypes to refine pseudo-labels and guide the network convergence, significantly outperforming state-of-the-art unsupervised 3D detectors.