Learning Unorthogonalized Matrices for Rotation Estimation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Human Pose EstimationPose EstimationSimilar Papers 제목 키워드 기반
Mathematical Foundation and Corrections for Full Range Head Pose Estimation
Numerous works concerning head pose estimation (HPE) offer algorithms or proposed neural network-based approaches for extracting Euler angles from either facial key points or directly from images of the head region. Howe…
Head Pose EstimationPose EstimationA Birotation Solution for Relative Pose Problems
Relative pose estimation, a fundamental computer vision problem, has been extensively studied for decades. Existing methods either estimate and decompose the essential matrix or directly estimate the rotation and transla…
Pose EstimationFull-range Head Pose Geometric Data Augmentations
Many head pose estimation (HPE) methods promise the ability to create full-range datasets, theoretically allowing the estimation of the rotation and positioning of the head from various angles. However, these methods are…
Dataset GenerationHead Pose EstimationPose EstimationSpecificityEstimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing
We consider the problem of signal estimation in generalized linear models defined via rotationally invariant design matrices. Since these matrices can have an arbitrary spectral distribution, this model is well suited fo…
Approximate Message Passing for Multi-Layer Estimation in Rotationally Invariant Models
We consider the problem of reconstructing the signal and the hidden variables from observations coming from a multi-layer network with rotationally invariant weight matrices. The multi-layer structure models inference fr…