Scipediacontent: Scipediacontent moved page Draft Content 348045062 to Rother Brachmann 2017a

2021-02-03T18:05:14Z

Scipediacontent moved page Draft Content 348045062 to Rother Brachmann 2017a

Scipediacontent: Created page with " == Abstract == Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization. In this work, we address th..."

2021-02-03T18:05:11Z

Created page with " == Abstract == Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization. In this work, we address th..."

New page

== 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://arxiv.org/abs/1711.10228 http://arxiv.org/abs/1711.10228]

* [http://arxiv.org/pdf/1711.10228 http://arxiv.org/pdf/1711.10228]

* [http://xplorestaging.ieee.org/ielx7/8576498/8578098/08578587.pdf?arnumber=8578587 http://xplorestaging.ieee.org/ielx7/8576498/8578098/08578587.pdf?arnumber=8578587],
: [http://dx.doi.org/10.1109/cvpr.2018.00489 http://dx.doi.org/10.1109/cvpr.2018.00489]

* [https://dblp.uni-trier.de/db/conf/cvpr/cvpr2018.html#BrachmannR18 https://dblp.uni-trier.de/db/conf/cvpr/cvpr2018.html#BrachmannR18],
: [https://arxiv.org/pdf/1711.10228.pdf https://arxiv.org/pdf/1711.10228.pdf],
: [https://arxiv.org/abs/1711.10228 https://arxiv.org/abs/1711.10228],
: [https://ieeexplore.ieee.org/document/8578587 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/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 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://ui.adsabs.harvard.edu/abs/2017arXiv171110228B/abstract],
: [https://www.arxiv-vanity.com/papers/1711.10228 https://www.arxiv-vanity.com/papers/1711.10228],
: [https://academic.microsoft.com/#/detail/2963856988 https://academic.microsoft.com/#/detail/2963856988]

← Older revision	Revision as of 18:05, 3 February 2021
(No difference)

Rother Brachmann 2017a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 348045062 to Rother Brachmann 2017a

Scipediacontent: Created page with " == Abstract == Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization. In this work, we address th..."