Authors: Weifeng Chen,Zhao Fu,Dawei Yang,Jia Deng
Where published:
NeurIPS 2016 12
ArXiv: 1604.03901
Document:
PDF
DOI
Artifact development version:
GitHub
Abstract URL: http://arxiv.org/abs/1604.03901v2
This paper studies single-image depth perception in the wild, i.e.,
recovering depth from a single image taken in unconstrained settings. We
introduce a new dataset "Depth in the Wild" consisting of images in the wild
annotated with relative depth between pairs of random points. We also propose a
new algorithm that learns to estimate metric depth using annotations of
relative depth. Compared to the state of the art, our algorithm is simpler and
performs better. Experiments show that our algorithm, combined with existing
RGB-D data and our new relative depth annotations, significantly improves
single-image depth perception in the wild.