Robust Uncertainty-Aware Multiview Triangulation

TL;DR

This paper introduces a robust multiview triangulation method that combines outlier rejection, local optimization, and uncertainty modeling to improve accuracy and efficiency in 3D point estimation.

Contribution

It presents a novel outlier rejection scheme, compares local optimization techniques, and models uncertainty based on multiple factors for rapid estimation.

Findings

Achieves state-of-the-art efficiency in outlier rejection

Significantly improves accuracy through iterative local optimization

Effectively models and interpolates uncertainty in triangulation

Abstract

We propose a robust and efficient method for multiview triangulation and uncertainty estimation. Our contribution is threefold: First, we propose an outlier rejection scheme using two-view RANSAC with the midpoint method. By prescreening the two-view samples prior to triangulation, we achieve the state-of-the-art efficiency. Second, we compare different local optimization methods for refining the initial solution and the inlier set. With an iterative update of the inlier set, we show that the optimization provides significant improvement in accuracy and robustness. Third, we model the uncertainty of a triangulated point as a function of three factors: the number of cameras, the mean reprojection error and the maximum parallax angle. Learning this model allows us to quickly interpolate the uncertainty at test time. We validate our method through an extensive evaluation.