教師なし同変学習によるRKHS上の対応不要SE(3)点群位置合わせ
Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning
点群を再生核ヒルベルト空間の関数として扱い、SE(3)同変特徴を用いることで対応点を必要とせずに位置合わせを行う教師なし学習手法を提案した。
著者: Ray Zhang, Zheming Zhou, Min Sun, Omid Ghasemalizadeh, Cheng-Hao Kuo, Ryan Eustice, Maani Ghaffari, Arnie Sen
分類: cs.CV, cs.RO
原文アブストラクト
This paper introduces a robust unsupervised SE(3) point cloud registration method that operates without requiring point correspondences. The method frames point clouds as functions in a reproducing kernel Hilbert space (RKHS), leveraging SE(3)-equivariant features for direct feature space registration. A novel RKHS distance metric is proposed, offering reliable performance amidst noise, outliers, and asymmetrical data. An unsupervised training approach is introduced to effectively handle limited ground truth data, facilitating adaptation to real datasets. The proposed method outperforms classical and supervised methods in terms of registration accuracy on both synthetic (ModelNet40) and real-world (ETH3D) noisy, outlier-rich datasets. To our best knowledge, this marks the first instance of successful real RGB-D odometry data registration using an equivariant method. The code is available at {https://sites.google.com/view/eccv24-equivalign}
