Feature Query Networks: Neural Surface Description for Camera Pose Refinement

Hugo Germain, Daniel DeTone, Geoffrey Pascoe, Tanner Schmidt, David Novotný, Richard A. Newcombe, Chris Sweeney, Richard Szeliski, Vasileios Balntas

CVPRW 2022 pp. 5067-5077

doi:10.1109/CVPRW56347.2022.00555 /cvprw/2022/germain2022cvprw-feature/

Abstract

Accurate 6-DoF camera pose estimation in known environments can be a very challenging task, especially when the query image was captured at viewpoints strongly differing from the set of reference camera poses. While structure-based methods have proved to deliver accurate camera pose estimates, they rely on pre-computed 3D descriptors coming from reference images often misaligned with query images. This discrepancy can subsequently harm downstream camera pose estimation tasks. In this paper we introduce the Feature Query Network (FQN), a ray-based descriptor regressor that can be used to query descriptors at known 3D locations under novel viewpoints. We show that the FQN is able to model viewpoint-dependency of high-dimensional keypoint descriptors and bring significant relative improvements to structure-based visual localization baselines.

CVPRW Semantic Scholar

Cite

Text

Germain et al. "Feature Query Networks: Neural Surface Description for Camera Pose Refinement." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00555

Markdown

[Germain et al. "Feature Query Networks: Neural Surface Description for Camera Pose Refinement." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/germain2022cvprw-feature/) doi:10.1109/CVPRW56347.2022.00555

BibTeX

@inproceedings{germain2022cvprw-feature,
  title     = {{Feature Query Networks: Neural Surface Description for Camera Pose Refinement}},
  author    = {Germain, Hugo and DeTone, Daniel and Pascoe, Geoffrey and Schmidt, Tanner and Novotný, David and Newcombe, Richard A. and Sweeney, Chris and Szeliski, Richard and Balntas, Vasileios},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {5067-5077},
  doi       = {10.1109/CVPRW56347.2022.00555},
  url       = {https://mlanthology.org/cvprw/2022/germain2022cvprw-feature/}
}