Year: 2023
Type: preprint
Abstract: Estimating 3D rotations is a common procedure for 3D computer vision. The accuracy depends heavily on the rotation representation. One form of representation -- rotation matrices -- is popular due to its continuity, especially for pose estimation tasks. The learning process usually incorporates orthogonalization to ensure orthonormal matrices. Our work reveals, through gradient analysis, that common orthogonalization procedures based on the Gram-Schmidt process and singular value decomposition will slow down training efficiency. To this end, we advocate removing orthogonalization from the learning process and learning unorthogonalized `Pseudo' Rotation Matrices (PRoM). An optimization analysis shows that PRoM converges faster and to a better solution. By replacing the orthogonalization incorporated representation with our proposed PRoM in various rotation-related tasks, we achieve state-of-the-art results on large-scale benchmarks for human pose estimation.
Source: arXiv (Cornell University)
Authors: Gu, Kerui, Li, Zhihao, Liu, Shiyong, Liu, Jianzhuang, Xu, Songcen, Yan, Youliang, Mi, Michael Bi, Kawaguchi, Kenji, Yao, Angela
Institutions: National University of Singapore, Huawei Technologies (China)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4389325943