Robust 360-8PA: Redesigning The Normalized 8-point Algorithm for 360-FoV Images

TL;DR

This paper introduces a new preconditioning strategy for the 8-point algorithm tailored for 360-degree images, significantly improving essential matrix estimation accuracy and robustness in spherical camera pose estimation.

Contribution

It proposes a novel non-rigid transformation normalization method that enhances the classic 8-point algorithm for 360-FoV images, increasing accuracy and robustness.

Findings

Camera pose accuracy improved by about 20%

Normalization increases robustness against outliers

Method reduces RANSAC iterations needed

Abstract

This paper presents a novel preconditioning strategy for the classic 8-point algorithm (8-PA) for estimating an essential matrix from 360-FoV images (i.e., equirectangular images) in spherical projection. To alleviate the effect of uneven key-feature distributions and outlier correspondences, which can potentially decrease the accuracy of an essential matrix, our method optimizes a non-rigid transformation to deform a spherical camera into a new spatial domain, defining a new constraint and a more robust and accurate solution for an essential matrix. Through several experiments using random synthetic points, 360-FoV, and fish-eye images, we demonstrate that our normalization can increase the camera pose accuracy by about 20% without significantly overhead the computation time. In addition, we present further benefits of our method through both a constant weighted least-square optimization that improves further the well known Gold Standard Method (GSM) (i.e., the non-linear optimization by using epipolar errors); and a relaxation of the number of RANSAC iterations, both showing that our normalization outcomes a more reliable, robust, and accurate solution.