Estimating Geometric Scene Context from a Single Image [1/3]

Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=lTsR8c7bkjc



Duration: 1:10:28
61 views
0


Humans have an amazing ability to instantly grasp the overall 3D structure of a scene ΓÇô ground orientation, relative positions of major landmarks, etc -- even from a single image. This ability is completely missing in most popular recognition algorithms, which pretend that the world is flat and/or view it through a patch-sized peephole. Yet it seems very likely that having a grasp of this geometric







Tags:
microsoft research