Saved in:
Bibliographic Details
Main Authors: Tirado-Garín, Javier, Civera, Javier
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.05995
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909153469923328
author Tirado-Garín, Javier
Civera, Javier
author_facet Tirado-Garín, Javier
Civera, Javier
contents Estimating the relative camera pose from $n \geq 5$ correspondences between two calibrated views is a fundamental task in computer vision. This process typically involves two stages: 1) estimating the essential matrix between the views, and 2) disambiguating among the four candidate relative poses that satisfy the epipolar geometry. In this paper, we demonstrate a novel approach that, for the first time, bypasses the second stage. Specifically, we show that it is possible to directly estimate the correct relative camera pose from correspondences without needing a post-processing step to enforce the cheirality constraint on the correspondences. Building on recent advances in certifiable non-minimal optimization, we frame the relative pose estimation as a Quadratically Constrained Quadratic Program (QCQP). By applying the appropriate constraints, we ensure the estimation of a camera pose that corresponds to a valid 3D geometry and that is globally optimal when certified. We validate our method through exhaustive synthetic and real-world experiments, confirming the efficacy, efficiency and accuracy of the proposed approach. Code is available at https://github.com/javrtg/C2P.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05995
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation
Tirado-Garín, Javier
Civera, Javier
Computer Vision and Pattern Recognition
Estimating the relative camera pose from $n \geq 5$ correspondences between two calibrated views is a fundamental task in computer vision. This process typically involves two stages: 1) estimating the essential matrix between the views, and 2) disambiguating among the four candidate relative poses that satisfy the epipolar geometry. In this paper, we demonstrate a novel approach that, for the first time, bypasses the second stage. Specifically, we show that it is possible to directly estimate the correct relative camera pose from correspondences without needing a post-processing step to enforce the cheirality constraint on the correspondences. Building on recent advances in certifiable non-minimal optimization, we frame the relative pose estimation as a Quadratically Constrained Quadratic Program (QCQP). By applying the appropriate constraints, we ensure the estimation of a camera pose that corresponds to a valid 3D geometry and that is globally optimal when certified. We validate our method through exhaustive synthetic and real-world experiments, confirming the efficacy, efficiency and accuracy of the proposed approach. Code is available at https://github.com/javrtg/C2P.
title From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.05995