Xu, W and Zhang, X and Pollefeys, M and Baráth, Dániel and Kneip, L (2025) Generalized Relative Pose and Scale from Affine Correspondences. INTERNATIONAL JOURNAL OF COMPUTER VISION, 133. pp. 5840-5856. ISSN 0920-5691 10.1007/s11263-025-02452-0

Text Xu_5840_36228643_z.pdf Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Aligning extrinsically calibrated view sets is essential for merging 3D reconstructions from different agents or localizing them within a large existing map of the environment. In such scenarios, we not only have to account for the 3D rotation and translation but also need to estimate the unknown scaling factor between the reconstructions. In this paper, we propose the first closed-form solvers for image-only data to the general problem, leveraging either 26 point or 9 affine correspondences (AC) to obtain the scale, 3D orientation, and translation. Considering that modern image-capturing tools like smartphones and mixed reality devices typically come with Inertial Measurement Units and return the gravity direction by default, we also propose a solver that requires just 2 ACs along with gravity measurements. The proposed methods have been rigorously tested on both synthetic data and extensive publicly available real-world datasets. The results demonstrate that our approach achieves state-of-the-art accuracy and permits robust estimation in real-time owing to small sample sizes. The code is available at https://github.com/gowanting/GRPS-Affine. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

Item Type:	Article
Uncontrolled Keywords:	GEOMETRY; Closed form; 3D reconstruction; Epipolar geometry; Epipolar geometry; RELATIVE POSE; affine correspondence; scaling factors; 3D rotation; Affine correspondences; Generalized relative pose and scale problem; 3D orientation; 3D translation; Generalized relative pose and scale problem;
Subjects:	Q Science > QA Mathematics and Computer Science > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
Divisions:	Distributed Events Analysis Research Laboratory
SWORD Depositor:	MTMT Injector
Depositing User:	MTMT Injector
Date Deposited:	29 Jul 2025 07:52
Last Modified:	29 Jul 2025 07:52
URI:	https://eprints.sztaki.hu/id/eprint/10953

Update Item