Sciweavers

ICCV
2009
IEEE

Estimating human shape and pose from a single image

13 years 1 months ago
Estimating human shape and pose from a single image
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 ...
Peng Guan, Alexander Weiss, Alexandru O. Balan, Mi
Added 18 Feb 2011
Updated 18 Feb 2011
Type Journal
Year 2009
Where ICCV
Authors Peng Guan, Alexander Weiss, Alexandru O. Balan, Michael J. Black
Comments (0)