Fusing Directions and Displacements in Translation Averaging

Manam, L and Govindu, VM (2024) Fusing Directions and Displacements in Translation Averaging. In: 11th International Conference on 3D Vision, 3DV 2024, 18 March 2024through 21 March 2024, Davos, Switzerland, pp. 75-84.

PDF Int_Con_3D_Vision.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Translation averaging solves for 3D camera translations given many pairwise relative translation directions. The mismatch between inputs (directions) and output estimates (absolute translations) makes translation averaging a challenging problem, which is often addressed by comparing either directions or displacements using relaxed cost functions that are relatively easy to optimize. However, the distinctly different nature of the cost functions leads to varied behaviour under different baselines and noise conditions. In this paper, we argue that translation averaging can benefit from a fusion of the two approaches. Specifically, we recursively fuse the individual updates suggested by direction and displacement-based methods using their uncertainties. The uncertainty of each estimate is modelled by the inverse of the Hessian of the corresponding optimization problem. As a result, our method utilizes the advantages of both methods in a principled manner. The superiority of our translation averaging scheme is demonstrated via the improved accuracies of camera translations on benchmark datasets compared to the state-of-the-art methods. © 2024 IEEE.

Item Type:	Conference Proceedings
Publication:	Proceedings - 2024 International Conference on 3D Vision, 3DV 2024
Series.:	Proceedings - 2024 International Conference on 3D Vision, 3DV 2024
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Cameras; Computer vision; Cost benefit analysis; Cost estimating; Inverse problems; Uncertainty analysis, 3D camera; 3D computer vision; Base-line conditions; Camera translation; Cost-function; Displacement-based method; Noise conditions; Structure from motion; Translation averaging; Uncertainty, Cost functions
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	30 Jul 2024 12:22
Last Modified:	30 Jul 2024 12:22
URI:	http://eprints.iisc.ac.in/id/eprint/85639

Actions (login required)

View Item