Perceiving Systems, Computer Vision

Estimating human shape and pose from a single image

2009

Conference Paper

ps


We describe a solution to the challenging problem of estimating human body shape from a single photograph or painting. Our approach computes shape and pose parameters of a 3D human body model directly from monocular image cues and advances the state of the art in several directions. First, given a user-supplied estimate of the subject's height and a few clicked points on the body we estimate an initial 3D articulated body pose and shape. Second, using this initial guess we generate a tri-map of regions inside, outside and on the boundary of the human, which is used to segment the image using graph cuts. Third, we learn a low-dimensional linear model of human shape in which variations due to height are concentrated along a single dimension, enabling height-constrained estimation of body shape. Fourth, we formulate the problem of parametric human shape from shading. We estimate the body pose, shape and reflectance as well as the scene lighting that produces a synthesized body that robustly matches the image evidence. Quantitative experiments demonstrate how smooth shading provides powerful constraints on human shape. We further demonstrate a novel application in which we extract 3D human models from archival photographs and paintings.

Author(s): Guan, P. and Weiss, A. and Balan, A. and Black, M. J.
Book Title: Int. Conf. on Computer Vision, ICCV
Pages: 1381--1388
Year: 2009

Department(s): Perceiving Systems
Research Project(s): Clothing Models (2011-2015)
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Links: pdf
video - mov 25MB
video - mp4 10MB
YouTube
Video:

BibTex

@inproceedings{Guan:ICCV:2009,
  title = {Estimating human shape and pose from a single image},
  author = {Guan, P. and Weiss, A. and Balan, A. and Black, M. J.},
  booktitle = {Int. Conf. on Computer Vision, ICCV},
  pages = {1381--1388},
  year = {2009},
  doi = {}
}