3D Body Shapes Estimation from Dressed-Human Silhouettes
dc.contributor.author | Song, Dan | en_US |
dc.contributor.author | Tong, Ruofeng | en_US |
dc.contributor.author | Chang, Jian | en_US |
dc.contributor.author | Yang, Xiaosong | en_US |
dc.contributor.author | Tang, Min | en_US |
dc.contributor.author | Zhang, Jian Jun | en_US |
dc.contributor.editor | Eitan Grinspun and Bernd Bickel and Yoshinori Dobashi | en_US |
dc.date.accessioned | 2016-10-11T05:19:08Z | |
dc.date.available | 2016-10-11T05:19:08Z | |
dc.date.issued | 2016 | |
dc.description.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. | en_US |
dc.description.number | 7 | |
dc.description.sectionheaders | Reconstruction | |
dc.description.seriesinformation | Computer Graphics Forum | |
dc.description.volume | 35 | |
dc.identifier.doi | 10.1111/cgf.13012 | |
dc.identifier.issn | 1467-8659 | |
dc.identifier.pages | 147-156 | |
dc.identifier.uri | https://doi.org/10.1111/cgf.13012 | |
dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf13012 | |
dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
dc.subject | I.3.m [Computer Graphics] | |
dc.subject | Miscellaneous | |
dc.subject | Image | |
dc.subject | based modeling | |
dc.title | 3D Body Shapes Estimation from Dressed-Human Silhouettes | en_US |