Counterfactual Depth from a Single RGB Image

3 Sep 2019Theerasit IssaranonChuhang ZouDavid Forsyth

We describe a method that predicts, from a single RGB image, a depth map that describes the scene when a masked object is removed - we call this "counterfactual depth" that models hidden scene geometry together with the observations. Our method works for the same reason that scene completion works: the spatial structure of objects is simple... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.