Deep Projective Rotation Estimation through Relative Supervision

11/21/2022
by   Brian Okorn, et al.
0

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 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 https://sites.google.com/view/deep-projective-rotation/home .

READ FULL TEXT
research
06/15/2022

Self-Supervised Learning of Image Scale and Orientation

We study the problem of learning to assign a characteristic pose, i.e., ...
research
03/25/2023

Learning Rotation-Equivariant Features for Visual Correspondence

Extracting discriminative local features that are invariant to imaging v...
research
04/19/2022

Self-Supervised Equivariant Learning for Oriented Keypoint Detection

Detecting robust keypoints from an image is an integral part of many com...
research
04/01/2019

Probabilistic Regression of Rotations using Quaternion Averaging and a Deep Multi-Headed Network

Accurate estimates of rotation are crucial to vision-based motion estima...
research
09/18/2023

RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy

Unlike in natural images, in endoscopy there is no clear notion of an up...
research
04/14/2021

Self-supervised Learning of 3D Object Understanding by Data Association and Landmark Estimation for Image Sequence

In this paper, we propose a self-supervised learningmethod for multi-obj...
research
05/23/2022

ConvPoseCNN2: Prediction and Refinement of Dense 6D Object Poses

Object pose estimation is a key perceptual capability in robotics. We pr...

Please sign up or login with your details

Forgot password? Click here to reset