3D Body Shapes Estimation from Dressed-Human Silhouettes

Authors: Song, D., Tong, R., Chang, J., Yang, X., Tang, M. and Zhang, J.J.

Journal: Computer Graphics Forum

Volume: 35

Issue: 7

Pages: 147-156

eISSN: 1467-8659

ISSN: 0167-7055

DOI: 10.1111/cgf.13012

Abstract:

Estimation of 3D body shapes from dressed-human photos is an important but challenging problem in virtual fitting. We propose a novel automatic framework to efficiently estimate 3D body shapes under clothes. We construct a database of 3D naked and dressed body pairs, based on which we learn how to predict 3D positions of body landmarks (which further constrain a parametric human body model) automatically according to dressed-human silhouettes. Critical vertices are selected on 3D registered human bodies as landmarks to represent body shapes, so as to avoid the time-consuming vertices correspondences finding process for parametric body reconstruction. Our method can estimate 3D body shapes from dressed-human silhouettes within 4 seconds, while the fastest method reported previously need 1 minute. In addition, our estimation error is within the size tolerance for clothing industry. We dress 6042 naked bodies with 3 sets of common clothes by physically based cloth simulation technique. To the best of our knowledge, We are the first to construct such a database containing 3D naked and dressed body pairs and our database may contribute to the areas of human body shapes estimation and cloth simulation.

https://eprints.bournemouth.ac.uk/24967/

Source: Scopus

3D Body Shapes Estimation from Dressed-Human Silhouettes

Authors: Song, D., Tong, R., Chang, J., Yang, X., Tang, M. and Zhang, J.J.

Journal: COMPUTER GRAPHICS FORUM

Volume: 35

Issue: 7

Pages: 147-156

eISSN: 1467-8659

ISSN: 0167-7055

DOI: 10.1111/cgf.13012

https://eprints.bournemouth.ac.uk/24967/

Source: Web of Science (Lite)

3D Body Shapes Estimation from Dressed-Human Silhouettes

Authors: Song, D., Tong, R., Chang, J., Yang, X., Tang, M. and Zhang, J.J.

Journal: Computer Graphics Forum

Volume: 35

Issue: 7

Pages: 147-156

ISSN: 0167-7055

Abstract:

Estimation of 3D body shapes from dressed-human photos is an important but challenging problem in virtual fitting. We propose a novel automatic framework to efficiently estimate 3D body shapes under clothes. We construct a database of 3D naked and dressed body pairs, based on which we learn how to predict 3D positions of body landmarks (which further constrain a parametric human body model) automatically according to dressed-human silhouettes. Critical vertices are selected on 3D registered human bodies as landmarks to represent body shapes, so as to avoid the time-consuming vertices correspondences finding process for parametric body reconstruction. Our method can estimate 3D body shapes from dressed-human silhouettes within 4 seconds, while the fastest method reported previously need 1 minute. In addition, our estimation error is within the size tolerance for clothing industry. We dress 6042 naked bodies with 3 sets of common clothes by physically based cloth simulation technique. To the best of our knowledge, We are the first to construct such a database containing 3D naked and dressed body pairs and our database may contribute to the areas of human body shapes estimation and cloth simulation.

https://eprints.bournemouth.ac.uk/24967/

Source: BURO EPrints