Expert Sample Consensus applied to camera re-localization

• Verfasst von: Brachmann, Eric [VerfasserIn]
• Verfasst von: Rother, Carsten [VerfasserIn]
• Titel: Expert Sample Consensus applied to camera re-localization
• Verf.angabe: Eric Brachmann and Carsten Rother
• Jahr: 2019
• Umfang: 13 S.
• Fussnoten: Gesehen am 14.09.2020
• Titel Quelle: Enthalten in: De.arxiv.org
• Ort Quelle: [S.l.] : Arxiv.org, 1991
• Jahr Quelle: 2019
• Band/Heft Quelle: (2019) Artikel-Nummer 1908.02484, 13 Seiten
• Datenträger: Online-Ressource
• Sprache: eng
• Bibliogr. Hinweis: Forschungsdaten: Brachmann, Eric, 1987 - : Expert Sample Consensus (ESAC) for visual re-localization [data]
• Sach-SW: Computer Science - Computer Vision and Pattern Recognition
• K10plus-PPN: 1731813082

Abstract

Fitting model parameters to a set of noisy data points is a common problem in computer vision. In this work, we fit the 6D camera pose to a set of noisy correspondences between the 2D input image and a known 3D environment. We estimate these correspondences from the image using a neural network. Since the correspondences often contain outliers, we utilize a robust estimator such as Random Sample Consensus (RANSAC) or Differentiable RANSAC (DSAC) to fit the pose parameters. When the problem domain, e.g. the space of all 2D-3D correspondences, is large or ambiguous, a single network does not cover the domain well. Mixture of Experts (MoE) is a popular strategy to divide a problem domain among an ensemble of specialized networks, so called experts, where a gating network decides which expert is responsible for a given input. In this work, we introduce Expert Sample Consensus (ESAC), which integrates DSAC in a MoE. Our main technical contribution is an efficient method to train ESAC jointly and end-to-end. We demonstrate experimentally that ESAC handles two real-world problems better than competing methods, i.e. scalability and ambiguity. We apply ESAC to fitting simple geometric models to synthetic images, and to camera re-localization for difficult, real datasets.