Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
Paper i proceeding, 2021
Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new viewpoints or ties the model parameters to a specific scene. In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms. We introduce PixLoc, a scene-agnostic neural network that estimates an accurate 6-DoF pose from an image and a 3D model. Our approach is based on the direct alignment of multiscale deep features, casting camera localization as metric learning. PixLoc learns strong data priors by end-to-end training from pixels to pose and exhibits exceptional generalization to new scenes by separating model parameters and scene geometry. The system can localize in large environments given coarse pose priors but also improve the accuracy of sparse feature matching by jointly refining keypoints and poses with little overhead. The code will be publicly available at github.com/cvg/pixloc.
Författare
Paul-Edouard Sarlin
Eidgenössische Technische Hochschule Zürich (ETH)
Ajaykumar Unagar
Eidgenössische Technische Hochschule Zürich (ETH)
Mans Larsson
Eigenvision AB
Hugo Germain
École des Ponts ParisTech
Carl Toft
Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik, Digitala bildsystem och bildanalys
Viktor Larsson
Eidgenössische Technische Hochschule Zürich (ETH)
Marc Pollefeys
Microsoft Corporation
Eidgenössische Technische Hochschule Zürich (ETH)
Vincent Lepetit
École des Ponts ParisTech
Lars Hammarstrand
Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik, Signalbehandling
Fredrik Kahl
Datorseende och medicinsk bildanalys
Torsten Sattler
Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik, Digitala bildsystem och bildanalys
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
1063-6919 (ISSN)
3246-3256978-1-6654-4509-2 (ISBN)
Online, ,
Ämneskategorier
Bioinformatik (beräkningsbiologi)
Mediateknik
Datorseende och robotik (autonoma system)
DOI
10.1109/CVPR46437.2021.00326