Skip to yearly menu bar Skip to main content


Poster

Single-Image Depth Perception in the Wild

Weifeng Chen · Zhao Fu · Dawei Yang · Jia Deng

Area 5+6+7+8 #173

Keywords: [ Deep Learning or Neural Networks ] [ (Application) Computer Vision ] [ (Application) Object and Pattern Recognition ]


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.

Live content is unavailable. Log in and register to view live content