Robust 360-8PA: Redesigning The Normalized 8-point Algorithm for 360-FoV Images
This work addresses camera pose estimation for 360-degree images, which is incremental as it builds on the classic 8-point algorithm with a novel preconditioning strategy.
The paper tackles the problem of estimating essential matrices from 360-degree field-of-view images by redesigning the normalized 8-point algorithm to handle uneven key-feature distributions and outliers, resulting in a 20% increase in camera pose accuracy without significant computational overhead.
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.