Header logo is

Body Talk: Crowdshaping Realistic 3D Avatars with Words

2016

Article

ps


Realistic, metrically accurate, 3D human avatars are useful for games, shopping, virtual reality, and health applications. Such avatars are not in wide use because solutions for creating them from high-end scanners, low-cost range cameras, and tailoring measurements all have limitations. Here we propose a simple solution and show that it is surprisingly accurate. We use crowdsourcing to generate attribute ratings of 3D body shapes corresponding to standard linguistic descriptions of 3D shape. We then learn a linear function relating these ratings to 3D human shape parameters. Given an image of a new body, we again turn to the crowd for ratings of the body shape. The collection of linguistic ratings of a photograph provides remarkably strong constraints on the metric 3D shape. We call the process crowdshaping and show that our Body Talk system produces shapes that are perceptually indistinguishable from bodies created from high-resolution scans and that the metric accuracy is sufficient for many tasks. This makes body “scanning” practical without a scanner, opening up new applications including database search, visualization, and extracting avatars from books.

Author(s): Stephan Streuber and M. Alejandra Quiros-Ramirez and Matthew Q. Hill and Carina A. Hahn and Silvia Zuffi and Alice O’Toole and Michael J. Black
Journal: ACM Trans. Graph. (Proc. SIGGRAPH)
Volume: 35
Number (issue): 4
Pages: 54:1--54:14
Year: 2016
Month: July

Department(s): Perceiving Systems
Research Project(s):
Bibtex Type: Article (article)
Paper Type: Journal

Links: pdf
web tool
video
talk (ppt)
Video:

BibTex

@article{Streuber:SIGGRAPH:2016,
  title = {{Body Talk}: Crowdshaping Realistic {3D} Avatars with Words},
  author = {Streuber, Stephan and Quiros-Ramirez, M. Alejandra and Hill, Matthew Q. and Hahn, Carina A. and Zuffi, Silvia and O’Toole, Alice and Black, Michael J.},
  journal = {ACM Trans. Graph. (Proc. SIGGRAPH)},
  volume = {35},
  number = {4},
  pages = {54:1--54:14},
  month = jul,
  year = {2016},
  doi = {},
  month_numeric = {7}
}