Abstract 

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. RGB-D Data Relative Depth Annotations train Deep Network with Input Image Metric Depth Pixel-wise PredictionFigure 1: We crowdsource annotations of relative depth and train a deep network to recover depthfrom a single image taken in unconstrained settings (“in the wild”).