Estimation of Human Body Shape in Motion with Wide Clothing - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Estimation of Human Body Shape in Motion with Wide Clothing

Jinlong Yang
  • Function : Author
  • PersonId : 9473
  • IdHAL : jlyang
Franck Hétroy-Wheeler
Stefanie Wuhrer

Abstract

Estimating 3D human body shape in motion from a sequence of unstructured oriented 3D point clouds is important for many applications. We propose the first automatic method to solve this problem that works in the presence of loose clothing. The problem is formulated as an optimization problem that solves for identity and posture parameters in a shape space capturing likely body shape variations. The automation is achieved by leveraging a recent robust pose detection method Stitched Puppet. To account for clothing, we take advantage of motion cues by encouraging the estimated body shape to be inside the observations. The method is evaluated on a new benchmark containing different subjects, motions, and clothing styles that allows to quantitatively measure the accuracy of body shape estimates. Furthermore, we compare our results to existing methods that require manual input and demonstrate that results of similar visual quality can be obtained.
Fichier principal
Vignette du fichier
Estimate of Human Body Shape in Motion with Wide Clothing.pdf (5.87 Mo) Télécharger le fichier
Vignette du fichier
tracking_under_clothes_teaser.jpg (27.9 Ko) Télécharger le fichier
supplementaryVideo.mp4 (68.24 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Format Figure, Image
Origin Files produced by the author(s)
Format Video
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01344795 , version 1 (12-07-2016)
hal-01344795 , version 2 (27-07-2016)
hal-01344795 , version 3 (23-08-2016)
hal-01344795 , version 4 (31-08-2016)

Licence

Identifiers

Cite

Jinlong Yang, Jean-Sébastien Franco, Franck Hétroy-Wheeler, Stefanie Wuhrer. Estimation of Human Body Shape in Motion with Wide Clothing. ECCV 2016 - European Conference on Computer Vision 2016, Oct 2016, Amsterdam, Netherlands. pp.439-454, ⟨10.1007/978-3-319-46493-0_27⟩. ⟨hal-01344795v4⟩
1824 View
2106 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More