Single-Image Depth Perception in the Wild

• DOI: 10.48550/arxiv.1604.03901
• Publication Date: 2016-01-01
• Authors: Chen, Weifeng; Fu, Zhao; Yang, Dawei; Deng, Jia
• Keywords: FOS: Computer and information sciences; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

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.