Deep Projective Rotation Estimation through Relative SupervisionDownload PDF

Published: 10 Sept 2022, Last Modified: 05 May 2023CoRL 2022 PosterReaders: Everyone
Keywords: rotations, deep learning, relative-supervision, self-supervision, modified rodrigues parameters, stereographic projection, pose estimation
TL;DR: By using a stereographic projection to open the closed manifold of SO(3), we avoid the local optima common when naively applying relative self-supervision for object orientation estimation, allowing for faster convergence.
Abstract: Orientation estimation is the core to a variety of vision and robotics tasks such as camera and object pose estimation. Deep learning has offered a way to develop image-based orientation estimators; however, such estimators often require training on a large labeled dataset, which can be time-intensive to collect. In this work, we explore whether self-supervised learning from unlabeled data can be used to alleviate this issue. Specifically, we assume access to estimates of the relative orientation between neighboring poses, such that can be obtained via a local alignment method. While self-supervised learning has been used successfully for translational object keypoints, in this work, we show that naively applying relative supervision to the rotational group $SO(3)$ will often fail to converge due to the non-convexity of the rotational space. To tackle this challenge, we propose a new algorithm for self-supervised orientation estimation which utilizes Modified Rodrigues Parameters to stereographically project the closed manifold of $SO(3)$ to the open manifold of $\mathbb{R}^{3}$, allowing the optimization to be done in an open Euclidean space. We empirically validate the benefits of the proposed algorithm for rotational averaging problem in two settings: (1) direct optimization on rotation parameters, and (2) optimization of parameters of a convolutional neural network that predicts object orientations from images. In both settings, we demonstrate that our proposed algorithm is able to converge to a consistent relative orientation frame much faster than algorithms that purely operate in the $SO(3)$ space. Additional information can be found at
Student First Author: yes
Supplementary Material: zip
12 Replies