Workshop ❝ 24 citations

Adversarial Networks for Camera Pose Regression and Refinement

Mai Bui, Christoph Baur, Nassir Navab, Slobodan Ilic, Shadi Albarqouni

Proceedings of the IEEE International Conference on Computer Vision Workshops, 2019

Altmetric · 1 patent (as of November 2026)

Teaser figure

Abstract

Despite recent advances on the topic of direct camera pose regression using neural networks, accurately estimating the camera pose of a single RGB image still remains a challenging task. To address this problem, we introduce a novel framework based, in its core, on the idea of implicitly learning the joint distribution of RGB images and their corresponding camera poses using a discriminator network and adversarial learning. Our method allows not only to regress the camera pose from a single image, however, also offers a solely RGB-based solution for camera pose refinement using the discriminator network. Further, we show that our method can effectively be used to optimize the predicted camera poses and thus improve the localization accuracy. To this end, we validate our proposed method on the publicly available 7-Scenes dataset improving upon the results of direct camera pose regression methods.

Interactive explainer

Auto-generated. This explainer was generated automatically with Claude (Anthropic) from the published paper. It simplifies the method and may contain errors — for a correct understanding, and for all results and numbers, please refer to the published paper (publisher version).

Research themes

Research areas

Funded by

Keywords

Computer VisionPose EstimationUncertaintyGenerative Adversarial Networks

Lab authors

Cite (BibTeX)
@inproceedings{bui2019adversarial,
 author = {Bui, Mai and Baur, Christoph and Navab, Nassir and Ilic, Slobodan and Albarqouni, Shadi},
 booktitle = {Proceedings of the IEEE International Conference on Computer Vision Workshops},
 pages = {0--0},
 title = {Adversarial Networks for Camera Pose Regression and Refinement},
 year = {2019}
}

Related publications