RelocNet: Continuous Metric Learning Relocalisation Using Neural Nets
Abstract
We propose a method of learning suitable convolutional representations for camera pose retrieval based on nearest neighbour matching and continuous metric learning-based feature descriptors. We introduce information from camera frusta overlaps between pairs of images to optimise our feature embedding network. Thus, the final camera pose descriptor differences represent camera pose changes. In addition, we build a pose regressor that is trained with a geometric loss to infer finer relative poses between a query and nearest neighbour images. Experiments show that our method is able to generalise in a meaningful way, and outperforms related methods across several experiments.
Cite
Text
Balntas et al. "RelocNet: Continuous Metric Learning Relocalisation Using Neural Nets." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01264-9_46Markdown
[Balntas et al. "RelocNet: Continuous Metric Learning Relocalisation Using Neural Nets." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/balntas2018eccv-relocnet/) doi:10.1007/978-3-030-01264-9_46BibTeX
@inproceedings{balntas2018eccv-relocnet,
title = {{RelocNet: Continuous Metric Learning Relocalisation Using Neural Nets}},
author = {Balntas, Vassileios and Li, Shuda and Prisacariu, Victor},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01264-9_46},
url = {https://mlanthology.org/eccv/2018/balntas2018eccv-relocnet/}
}