People Watching: Human Actions as a Cue for Single View Geometry - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles International Journal of Computer Vision Year : 2014

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

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.
Fichier principal
Vignette du fichier
fouhey14.pdf (11.1 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01066257 , version 1 (19-09-2014)

Identifiers

  • HAL Id : hal-01066257 , version 1

Cite

David Fouhey, V. Delaitre, Abhinav Gupta, Alexei Efros, Ivan Laptev, et al.. People Watching: Human Actions as a Cue for Single View Geometry. International Journal of Computer Vision, 2014, pp.17. ⟨hal-01066257⟩
6284 View
671 Download

Share

Gmail Facebook X LinkedIn More