Estimating the 3-D human body shape and pose under clothing is important for many applications, including virtual try-on, noncontact body measurement, and avatar creation for virtual reality. Existing body shape estimation methods formulate this task as an optimization problem by fitting a parametric body model to a single dressed-human scan or a sequence of dressed-human meshes for a better accuracy. This is impractical for many applications that require fast acquisition, such as gaming and virtual try-on due to the expensive computation. In this article, we propose the first learning-based approach to estimate the human body shape under clothing from a single dressed-human scan, dubbed Body PointNet. The proposed Body PointNet operates directly on raw point clouds and predicts the undressed body in a coarse-to-fine manner. Due to the nature of the data-aligned paired dressed scans and undressed bodies and genus-0 manifold meshes (i.e., single-layer surfaces)-we face a major challenge of lacking training data. To address this challenge, we propose a novel method to synthesize the dressed-human pseudoscans and corresponding ground truth bodies. A new large-scale dataset, dubbed body under virtual garments, is presented, employed for the learning task of body shape estimation from 3-D dressed-human scans. Comprehensive evaluations show that the proposed Body PointNet outperforms the state-of-the-art methods in terms of both accuracy and running time.
Hu, P , Nourbakhsh Kaashki, N , Dadarlat, V & Munteanu, A 2021, ' Learning to Estimate the Body Shape Under Clothing from a Single 3D Scan ', IEEE transactions on industrial informatics , vol. 17, no. 6, 9166710, pp. 3793-3802.
Hu, P. , Nourbakhsh Kaashki, N. , Dadarlat, V. , & Munteanu, A. (2021). Learning to Estimate the Body Shape Under Clothing from a Single 3D Scan . IEEE transactions on industrial informatics , 17 (6), 3793-3802. [9166710].
@article{05919f0d38c145ddaac5fd30edfa8b20,
title = " Learning to Estimate the Body Shape Under Clothing from a Single 3D Scan " ,
abstract = " Estimating the 3-D human body shape and pose under clothing is important for many applications, including virtual try-on, noncontact body measurement, and avatar creation for virtual reality. Existing body shape estimation methods formulate this task as an optimization problem by fitting a parametric body model to a single dressed-human scan or a sequence of dressed-human meshes for a better accuracy. This is impractical for many applications that require fast acquisition, such as gaming and virtual try-on due to the expensive computation. In this article, we propose the first learning-based approach to estimate the human body shape under clothing from a single dressed-human scan, dubbed Body PointNet. The proposed Body PointNet operates directly on raw point clouds and predicts the undressed body in a coarse-to-fine manner. Due to the nature of the data-aligned paired dressed scans and undressed bodies and genus-0 manifold meshes (i.e., single-layer surfaces)-we face a major challenge of lacking training data. To address this challenge, we propose a novel method to synthesize the dressed-human pseudoscans and corresponding ground truth bodies. A new large-scale dataset, dubbed body under virtual garments, is presented, employed for the learning task of body shape estimation from 3-D dressed-human scans. Comprehensive evaluations show that the proposed Body PointNet outperforms the state-of-the-art methods in terms of both accuracy and running time. " ,
keywords = " Body PointNet, Body shape under clothing " ,
author = " Pengpeng Hu and {Nourbakhsh Kaashki}, Nastaran and Vasile Dadarlat and Adrian Munteanu " ,
note = " Funding Information: Manuscript received December 17, 2019 revised July 6, 2020 accepted August 9, 2020. Date of publication August 13, 2020 date of current version March 5, 2021. This work was supported in part by the Innoviris under Project eTailor in close collaboration with Treedy{ extquoteright}s and in part by FWO under Project G084117. Paper no. TII-19-5382. (Corresponding author: Pengpeng Hu.) Pengpeng Hu, Nastaran Nourbakhsh Kaashki, and Adrian Munteanu are with the Department of Electronics and Informatics, Vrije Uni-versiteit Brussel, 1050 Brussels, Belgium (e-mail: [email protected] [email protected] [email protected] ). Publisher Copyright: { extcopyright} 2005-2012 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved. " ,
year = " 2021 " ,
month = jun,
doi = " 10.1109/TII.2020.3016591 " ,
language = " English " ,
volume = " 17 " ,
pages = " 37933802 " ,
journal = " IEEE transactions on industrial informatics " ,
issn = " 1551-3203 " ,
publisher = " IEEE " ,
number = " 6 " ,
}