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

David Fouhey 1 V. Delaitre 2 Abhinav Gupta 1 Alexei Efros 3, 4 Ivan Laptev 2 Josef Sivic 2
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
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.
Type de document :
Article dans une revue
International Journal of Computer Vision, Springer Verlag, 2014, pp.17
Liste complète des métadonnées

Littérature citée [54 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01066257
Contributeur : Minsu Cho <>
Soumis le : vendredi 19 septembre 2014 - 14:28:58
Dernière modification le : vendredi 25 mai 2018 - 12:02:06
Document(s) archivé(s) le : vendredi 14 avril 2017 - 12:57:31

Fichier

fouhey14.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01066257, version 1

Collections

Citation

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, Springer Verlag, 2014, pp.17. 〈hal-01066257〉

Partager

Métriques

Consultations de la notice

4448

Téléchargements de fichiers

770