Single-Image Depth Perception in the Wild

Code

• github.com/yifjiang/relative-depth-using-pytorch
  pytorch★ 0
• github.com/Turmac/DIW_TF_Implementation
  tf★ 0
• github.com/A-Jacobson/Depth_in_The_Wild
  pytorch★ 0
• github.com/dfan/single-image-surface-normal-estimation
  pytorch★ 0

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.

Tasks

Reproductions