People Watching: Human Actions as a Cue for Single View Geometry

David F. Fouhey (1) , Vincent Delaitre (2) , Abhinav Gupta (1) , Alexei A. Efros (1) , Ivan Laptev (3) , Josef Sivic (3)

1 Computer Science Department - Carnegie Mellon University
2 LIENS - Laboratoire d'informatique de l'école normale supérieure
3 WILLOW - Models of visual object recognition and scene understanding

We present an approach which exploits the coupling between human actions and scene geometry. We investigate the use of human pose as a cue for single-view 3D scene understanding. Our method builds upon recent advances in still-image pose estimation to extract functional and geometric constraints about the scene. These constraints are then used to improve state-of-the-art single-view 3D scene understanding approaches. The proposed method is validated on a collection of monocular time-lapse sequences collected from YouTube and a dataset of still images of indoor scenes. We demonstrate that observing people performing different actions can significantly improve estimates of 3D scene geometry.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

David F. Fouhey, Vincent Delaitre, Abhinav Gupta, Alexei A. Efros, Ivan Laptev, et al.. People Watching: Human Actions as a Cue for Single View Geometry. ECCV'12 - 12th European Conference on Computer Vision, Oct 2012, Florence, Italy. pp.732-735, ⟨10.1007/978-3-642-33715-4_53⟩. ⟨hal-01060874⟩