Learning less is more

• Verfasst von: Brachmann, Eric [VerfasserIn]
• Verfasst von: Rother, Carsten [VerfasserIn]
• Titel: Learning less is more
• Titelzusatz: 6D camera localization via 3D surface regression
• Verf.angabe: Eric Brachmann and Carsten Rother
• E-Jahr: 2018
• Jahr: 27 Mar 2018
• Umfang: 11 S.
• Fussnoten: Gesehen am 14.09.2020
• Titel Quelle: Enthalten in: De.arxiv.org
• Ort Quelle: [S.l.] : Arxiv.org, 1991
• Jahr Quelle: 2018
• Band/Heft Quelle: (2018) Artikel-Nummer 1711.10228, 11 Seiten
• Datenträger: Online-Ressource
• Sprache: eng
• Bibliogr. Hinweis: Forschungsdaten: Brachmann, Eric, 1987 - : DSAC++ visual camera re-localization [data]
• Sach-SW: Computer Science - Computer Vision and Pattern Recognition
• K10plus-PPN: 1731819463

Abstract

Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization. In this work, we address the task of predicting the 6D camera pose from a single RGB image in a given 3D environment. With the advent of neural networks, previous works have either learned the entire camera localization process, or multiple components of a camera localization pipeline. Our key contribution is to demonstrate and explain that learning a single component of this pipeline is sufficient. This component is a fully convolutional neural network for densely regressing so-called scene coordinates, defining the correspondence between the input image and the 3D scene space. The neural network is prepended to a new end-to-end trainable pipeline. Our system is efficient, highly accurate, robust in training, and exhibits outstanding generalization capabilities. It exceeds state-of-the-art consistently on indoor and outdoor datasets. Interestingly, our approach surpasses existing techniques even without utilizing a 3D model of the scene during training, since the network is able to discover 3D scene geometry automatically, solely from single-view constraints.