サインイン
インサイト - Unsupervised 3D Object Detection
Unsupervised 3D Object Detection with Uncertainty-Aware Bounding Boxes: A Novel Approach for Improved Accuracy
Inaccurate pseudo bounding boxes hinder unsupervised 3D object detection, but a novel uncertainty-aware framework, UA3D, mitigates this by estimating and regularizing uncertainty at the coordinate level, leading to substantial performance improvements.
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.