CVMar 9, 2023

Revisiting Rotation Averaging: Uncertainties and Robust Losses

arXiv:2303.05195v126 citationsh-index: 28Has Code
Originality Incremental advance
AI Analysis

This work addresses a specific bottleneck in global SfM pipelines for computer vision applications, representing an incremental improvement over existing methods.

The paper tackles the rotation averaging problem in Structure-from-Motion by modeling noise distributions through uncertainty propagation from point correspondences and integrating a robust loss, resulting in improved accuracy on large-scale benchmarks.

In this paper, we revisit the rotation averaging problem applied in global Structure-from-Motion pipelines. We argue that the main problem of current methods is the minimized cost function that is only weakly connected with the input data via the estimated epipolar geometries.We propose to better model the underlying noise distributions by directly propagating the uncertainty from the point correspondences into the rotation averaging. Such uncertainties are obtained for free by considering the Jacobians of two-view refinements. Moreover, we explore integrating a variant of the MAGSAC loss into the rotation averaging problem, instead of using classical robust losses employed in current frameworks. The proposed method leads to results superior to baselines, in terms of accuracy, on large-scale public benchmarks. The code is public. https://github.com/zhangganlin/GlobalSfMpy

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes