Visual camera re-localization from RGB and RGB-D images using DSAC

• Verfasst von: Brachmann, Eric [VerfasserIn]
• Verfasst von: Rother, Carsten [VerfasserIn]
• Titel: Visual camera re-localization from RGB and RGB-D images using DSAC
• Verf.angabe: Eric Brachmann and Carsten Rother
• E-Jahr: 2022
• Jahr: 01 September 2022
• Umfang: 19 S.
• Fussnoten: Gesehen am 17.10.2022
• Titel Quelle: Enthalten in: Institute of Electrical and Electronics EngineersIEEE transactions on pattern analysis and machine intelligence
• Ort Quelle: New York, NY : IEEE, 1979
• Jahr Quelle: 2022
• Band/Heft Quelle: 44(2022), 9, Seite 5847-5865
• ISSN Quelle: 1939-3539
• DOI: doi:10.1109/TPAMI.2021.3070754
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1819043193

Abstract

We describe a learning-based system that estimates the camera position and orientation from a single input image relative to a known environment. The system is flexible w.r.t. the amount of information available at test and at training time, catering to different applications. Input images can be RGB-D or RGB, and a 3D model of the environment can be utilized for training but is not necessary. In the minimal case, our system requires only RGB images and ground truth poses at training time, and it requires only a single RGB image at test time. The framework consists of a deep neural network and fully differentiable pose optimization. The neural network predicts so called scene coordinates, i.e., dense correspondences between the input image and 3D scene space of the environment. The pose optimization implements robust fitting of pose parameters using differentiable RANSAC (DSAC) to facilitate end-to-end training. The system, an extension of DSAC and referred to as DSAC*, achieves state-of-the-art accuracy on various public datasets for RGB-based re-localization, and competitive accuracy for RGB-D based re-localization.