A Closer Look at Rotation-Invariant Deep Point Cloud Analysis

Feiran Li, Kent Fujiwara, Fumio Okura, Yasuyuki Matsushita; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 16218-16227

Abstract


We consider the deep point cloud analysis tasks where the inputs of the networks are randomly rotated. Recent progress in rotation-invariant point cloud analysis is mainly driven by converting point clouds into their respective canonical poses, and principal component analysis (PCA) is a practical tool to achieve this. Due to the imperfect alignment of PCA, most of the current works are devoted to developing powerful network structures and features to overcome this deficiency, without thoroughly analyzing the PCA-based canonical poses themselves. In this work, we present a detailed study w.r.t. the PCA-based canonical poses of point clouds. Our investigation reveals that the ambiguity problem associated with the PCA-based canonical poses is handled insufficiently in some recent works. To this end, we develop a simple pose selector module for disambiguation, which presents noticeable enhancement (i.e., 5:3% classification accuracy) over state-of-the-art approaches on the challenging real-world dataset.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Li_2021_ICCV, author = {Li, Feiran and Fujiwara, Kent and Okura, Fumio and Matsushita, Yasuyuki}, title = {A Closer Look at Rotation-Invariant Deep Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {16218-16227} }