A Representation Separation Perspective to Correspondence-Free Unsupervised 3-D Point Cloud Registration

Zhiyuan Zhang, Jiadai Sun, Yuchao Dai, Dingfu Zhou, Xibin Song, Mingyi He

Abstract: 3-D point cloud registration in remote sensing field has been greatly advanced by deep learning-based methods, where the rigid transformation is either directly regressed from the two point clouds (correspondences-free approaches) or computed from the learned correspondences (correspondences-based approaches). Existing correspondence-free methods generally learn the holistic representation of the entire point cloud, which is fragile for partial and noisy point clouds. In this letter, we propose a correspondence-free unsupervised point cloud registration (UPCR) method from the representation separation perspective. First, we model the input point cloud as a combination of pose-invariant representation and pose-related representation. Second, the pose-related representation is used to learn the relative pose w.r.t. a “latent canonical shape” for the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">source</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">target</i> point clouds, respectively. Third, the rigid transformation is obtained from the above two learned relative poses. Our method not only filters out the disturbance in pose-invariant representation but also is robust to partial-to-partial point clouds or noise. Experiments on benchmark datasets demonstrate that our unsupervised method achieves comparable if not better performance than state-of-the-art supervised registration methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">The source code will be made public.</i>