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.

Comment: CVPR 2018


Original document

The different versions of the original document can be found in:

http://dx.doi.org/10.1109/cvpr.2018.00489
https://arxiv.org/pdf/1711.10228.pdf,
https://arxiv.org/abs/1711.10228,
https://ieeexplore.ieee.org/document/8578587,
http://openaccess.thecvf.com/content_cvpr_2018/papers/Brachmann_Learning_Less_Is_CVPR_2018_paper.pdf,
http://openaccess.thecvf.com/content_cvpr_2018/html/Brachmann_Learning_Less_Is_CVPR_2018_paper.html,
https://ui.adsabs.harvard.edu/abs/2017arXiv171110228B/abstract,
https://www.arxiv-vanity.com/papers/1711.10228,
https://academic.microsoft.com/#/detail/2963856988
Back to Top

Document information

Published on 01/01/2017

Volume 2017, 2017
DOI: 10.1109/cvpr.2018.00489
Licence: CC BY-NC-SA license

Document Score

0

Views 1
Recommendations 0

Share this document

claim authorship

Are you one of the authors of this document?