CoRL 2020, Spotlight Talk 389: Unsupervised Metric Relocalization Using Transform Consistency Loss

“**Unsupervised Metric Relocalization Using Transform Consistency Loss**
Mike Kasper (University of Colorado)*; Fernando Nobre (Amazon); Christoffer Heckman (University of Colorado); Nima Keivan (Amazon)
Publication: http://corlconf.github.io/paper_389/

**Abstract**
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.”

YouTube Source for this Robot AI Video

AI video(s) you might be interested in …