Training networks to perform metric relocalization traditionally requires accurate image correspondences. In practice, these are obtained by restricting domain coverage, employing additional sensors, or capturing large multi-view datasets. We instead propose a self-supervised solution, which exploits a key insight: localizing a query image within a map should yield the same absolute pose, regardless of the reference image used for registration. Guided by this intuition, we derive a novel transform consistency loss. Using this loss function, we train a deep neural network to infer dense feature and saliency maps to perform robust metric relocalization in dynamic environments. We evaluate our framework on synthetic and real-world data, showing our approach outperforms other supervised methods when a limited amount of ground-truth information is available.
@article{arxiv.2011.00608,
title = {Unsupervised Metric Relocalization Using Transform Consistency Loss},
author = {Mike Kasper and Fernando Nobre and Christoffer Heckman and Nima Keivan},
journal= {arXiv preprint arXiv:2011.00608},
year = {2020}
}
Comments
Accepted for publication in the 4th Conference on Robot Learning (CoRL 2020), Cambridge MA, USA