Since most current scene understanding approaches operate
either on the 2D image or using a surface-based representation, they do
not allow reasoning about the physical constraints within the 3D scene.
Inspired by the \Blocks World" work in the 1960's, we present a qual-
itative physical representation of an outdoor scene where objects have
volume and mass, and relationships describe 3D structure and mechani-
cal congurations. Our representation allows us to apply powerful global
geometric constraints between 3D volumes as well as the laws of statics in
a qualitative manner. We also present a novel iterative \interpretation-
by-synthesis" approach where, starting from an empty ground plane, we
progressively \build up" a physically-plausible 3D interpretation of the
image. For surface layout estimation, our method demonstrates an im-
provement in performance over the state-of-the-art [9]. But more impor-
tantly, our approach automatically generates 3D p...
Abhinav Gupta, Alexei A. Efros, Martial Hebert