Article

International Journal of Computer Vision

, Volume 110, Issue 3, pp 259-274

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

  • David F. FouheyAffiliated withRobotics Institute, Carnegie Mellon University Email author 
  • , Vincent DelaitreAffiliated withWILLOW Project, Département d’Informatique de l’École Normale Supérieure, ENS/INRIA/CNRS UMR 8548
  • , Abhinav GuptaAffiliated withRobotics Institute, Carnegie Mellon University
  • , Alexei A. EfrosAffiliated withRobotics Institute, Carnegie Mellon UniversityEECS Department at UC Berkeley
  • , Ivan LaptevAffiliated withWILLOW Project, Département d’Informatique de l’École Normale Supérieure, ENS/INRIA/CNRS UMR 8548
  • , Josef SivicAffiliated withWILLOW Project, Département d’Informatique de l’École Normale Supérieure, ENS/INRIA/CNRS UMR 8548

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access

Abstract

We present an approach which exploits the coupling between human actions and scene geometry to use 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 on the scene. These constraints are then used to improve single-view 3D scene understanding approaches. The proposed method is validated on monocular time-lapse sequences from YouTube and still images of indoor scenes gathered from the Internet. We demonstrate that observing people performing different actions can significantly improve estimates of 3D scene geometry.

Keywords

Scene understanding Action recognition 3D reconstruction