← Search

Nima Keivan

2 accepted papers

2020

Unsupervised Metric Relocalization Using Transform Consistency Loss

CoRL 2020

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 exploit

Cited by 0SourcePDFScholar