A new photo-based approach for fast human body shape modeling

Authors:
Xiao Hu Liu;Yu Wen Wu;Yan Ting Huang
Affiliations:
Engineering Computing and Simulation Institute, Huazhong University of Science and Technology, Wuhan, P.R. China;Engineering Computing and Simulation Institute, Huazhong University of Science and Technology, Wuhan, P.R. China;Engineering Computing and Simulation Institute, Huazhong University of Science and Technology, Wuhan, P.R. China
Venue:
WISM'10 Proceedings of the 2010 international conference on Web information systems and mining
Year:
2010

Citing 4
Cited 0

Free-form deformation of solid geometric models

SIGGRAPH '86 Proceedings of the 13th annual conference on Computer graphics and interactive techniques
Efficiently Locating Objects Using the Hausdorff Distance

International Journal of Computer Vision
A 3D Display System for Cloth Online Virtual Fitting Room

CSIE '09 Proceedings of the 2009 WRI World Congress on Computer Science and Information Engineering - Volume 07
Online Cloth Virtual Fitting Room Based on a Local Cluster

NISS '09 Proceedings of the 2009 International Conference on New Trends in Information and Service Science

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a new photo-based approach for fast human body shape modeling is proposed. This approach takes the user's front and side digital photos as input, and then quickly generates a semblable body shape model with quadrangle mesh. The approach includes five steps: (1) extract profiles from user's photos and divide body contour into parts, (2) automatically select body part from pre-build body parts database, (3) conduct parametric axial deformation for each part, (4) refine body parts based on FFD, (5) smooth the body mesh. The algorithms are elaborated in detail. Experiments show that this approach can achieve good results very quickly and cheaply.