It Is All In The Weights: Robust Rotation Averaging Revisited


Sidhartha Chitturi and Venu Madhav Govindu


Rotation averaging is the problem of recovering 3D camera rotations from a number of pairwise relative rotation estimates. The state-of-the-art method of [5] involves robust averaging in the Lie-algebra of 3D rotations using an ` 1 2 loss function which is carried out using an iteratively reweighted least squares (IRLS) minimization. In this paper we argue that the performance of IRLS-based rotation averaging is intimately connected with two factors: a) the nature of the robust loss function used; and b) the initialization. We make two contributions. Firstly, we analyse the pitfalls associated with the unbounded weights in IRLS minimization of `p(0 < p < 2) loss functions in the context of rotation averaging. We elucidate the design choices and modifications implicit to the state-of-the-art method of [5] that overcomes these problems. Secondly, we argue that the ` 1 2 -based IRLS method is inflexible in adapting to the specific noise characteristics of individual datasets, leading to poorer performance. We remedy this limitation by means of a Geman-McClure loss function embedded in a graduated optimization framework. We present results on a number of large-scale real-world datasets to demonstrate that our proposed method outperforms state-of-the-art methods in terms of both efficiency and accuracy.

PDF (protected)

  Important Dates

All deadlines are 23:59 Pacific Time (PT). No extensions will be granted.

Paper registration July 23 30, 2021
Paper submission July 30, 2021
Supplementary August 8, 2021
Tutorial submission August 15, 2021
Tutorial notification August 31, 2021
Rebuttal period September 16-22, 2021
Paper notification October 1, 2021
Camera ready October 15, 2021
Demo submission July 30 Nov 15, 2021
Demo notification Oct 1 Nov 19, 2021
Tutorial November 30, 2021
Main conference December 1-3, 2021