Shape Customisation of Human Subjects Based on Human Parsing Technology - 17.288

S. Zhu et al., "Shape Customisation of Human Subjects Based on Human Parsing Technology", in Proc. of 3DBODY.TECH 2017 - 8th Int. Conf. and Exh. on 3D Body Scanning and Processing Technologies, Montreal QC, Canada, 11-12 Oct. 2017, pp. 288-295, https://doi.org/10.15221/17.288.

Title:

Shape Customisation of Human Subjects Based on Human Parsing Technology

Authors:

Shuaiyin ZHU 2, Yanghong ZHOU 2, K.P. CHAU 2, P.Y. MOK 1,2

Abstract:

Human modelling is an active research topic in medical, fitness and entertainment (such as game and movie) related studies. Many methods have been reported in the literature for human modeling, wjocj can be classified as scan-based, image-based and example-based approaches and all have pros and cons. In this paper, we propose a complete automatic method for human model shape customization based on the cutting-edge human parsing technology. The method allow users efficiently customize human models using orthogonal-view images in a complete automatic pipeline. We have demonstrated that our automatic customisation method is robust that generates accurate digital models for individuals using two images, and the method applies to male and female subjects, in tight-fit or arbitrary (normal and/or loose-fit) clothing, with different background conditions of the input images. Experimental results have demonstrated that our method improves accuracy, robustness, efficiency, and flexibility of human shape modelling.

Details:

Full paper: 17.288.pdf
Proceedings: 3DBODY.TECH 2017, 11-12 Oct. 2017, Montreal QC, Canada
Pages: 288-295
DOI: 10.15221/17.288

License/Copyright notice:

Proceedings: © Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, hometrica.ch.
Authors retain all rights to individual papers, which are licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The papers appearing in the proceedings reflect the author's opinions. Their inclusion in the proceedings does not necessary constitute endorsement by the editor or by the publisher.

Note: click the + on the top left of the page to open/close the menu.