Learning Unorthogonalized Matrices for Rotation Estimation

• URL: http://arxiv.org/abs/2312.00462v1
• Date: Fri, 1 Dec 2023 09:56:29 GMT
• Title: Learning Unorthogonalized Matrices for Rotation Estimation
• Authors: Kerui Gu, Zhihao Li, Shiyong Liu, Jianzhuang Liu, Songcen Xu, Youliang Yan, Michael Bi Mi, Kenji Kawaguchi, Angela Yao
• Abstract summary: Estimating 3D rotations is a common procedure for 3D computer vision. One form of representation -- rotation matrices -- is popular due to its continuity. We propose unorthogonalized Pseudo' Rotation Matrices (PRoM)
• Score: 83.94986875750455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Rotation Averaging: A Primal-Dual Method and Closed-Forms in Cycle Graphs [6.511636092857915]
  A benchmark of geometric reconstruction, averaging seeks the set of absolute settings that optimally explains a set of measured relative orientations between them. We propose a novel primal-dual cycle method motivated by the widely accepted spectral theory.
  arXiv  Detail & Related papers  (2024-05-29T21:46:39Z)
• RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging [62.315673415889314]
  This paper proposes a deep recurrent Rotation Averaging Graph (RAGO) for Multiple Rotation Averaging (MRA) Our framework is a real-time learning-to-optimize rotation averaging graph with a tiny size deployed for real-world applications.
  arXiv  Detail & Related papers  (2022-12-14T13:19:40Z)
• On Contrastive Representations of Stochastic Processes [53.21653429290478]
  Learning representations of processes is an emerging problem in machine learning. We show that our methods are effective for learning representations of periodic functions, 3D objects and dynamical processes.
  arXiv  Detail & Related papers  (2021-06-18T11:00:24Z)
• Parallelized Computation and Backpropagation Under Angle-Parametrized Orthogonal Matrices [0.0]
  We show how an apparently sequential elementary rotation parametrization can be restructured into blocks of commutative operations. We discuss parametric restrictions of interest to generative modeling and present promising performance results with a prototype GPU implementation.
  arXiv  Detail & Related papers  (2021-05-30T00:47:03Z)
• On the Robustness of Multi-View Rotation Averaging [77.09542018140823]
  We introduce the $epsilon$-cycle consistency term into the solver. We implicitly constrain the negative effect of erroneous measurements by weight reducing. Experiment results demonstrate that our proposed approach outperforms state of the arts on various benchmarks.
  arXiv  Detail & Related papers  (2021-02-09T05:47:37Z)
• Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes [86.2129580231191]
  Adjoint Rigid Transform (ART) Network is a neural module which can be integrated with a variety of 3D networks. ART learns to rotate input shapes to a learned canonical orientation, which is crucial for a lot of tasks. We will release our code and pre-trained models for further research.
  arXiv  Detail & Related papers  (2021-02-01T20:58:45Z)
• An Analysis of SVD for Deep Rotation Estimation [63.97835949897361]
  We present a theoretical analysis that shows SVD is the natural choice for projecting onto the rotation group. Our analysis shows simply replacing existing representations with the SVD orthogonalization procedure obtains state of the art performance in many deep learning applications.
  arXiv  Detail & Related papers  (2020-06-25T17:58:28Z)
• Fast Coherent Point Drift [4.369046007546103]
  Coherent point drift (CPD) is a classical method for nonrigid point set registration. By introducing a simple corresponding constraint, we develop a fast implementation of CPD. Experimental results in 3D point cloud data show that our method can significantly reduce burden of the registration process.
  arXiv  Detail & Related papers  (2020-06-11T09:35:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.