2026-09-18T20:55:11Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1271572021-07-05T14:03:20Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Ju Li.
Hi, Qi,S.M.Massachusetts Institute of Technology.
Massachusetts Institute of Technology. Department of Mechanical Engineering.
Massachusetts Institute of Technology. Department of Mechanical Engineering
2020-09-03T17:49:51Z
2020-09-03T17:49:51Z
2020
2020
https://hdl.handle.net/1721.1/127157
1191844129
Thesis: S.M., Massachusetts Institute of Technology, Department of Mechanical Engineering, May, 2020
Cataloged from the official PDF of thesis.
Includes bibliographical references (pages 55-59).
Three-dimensional (3D) reconstruction and modeling of the human body and garments from images is a central open problem in computer vision, yet remains a challenge using machine learning techniques. We proposed a framework to generate the realistic 3D human from a single RGB image via machine learning. The framework is composed of an end-to-end 3D reconstruction neural net with a skinned multi-person linear model (SMPL) model by the generative adversarial networks (GANs). The 3D facial reconstruction used the morphable facial model by principal component analysis (PCA) and the LS3D-W database. The 3D garments are reconstructed by the multi-garment net (MGN) to generate UV-mapping and remapped into the human model with motion transferred by archive of motion capture as surface shapes (AMASS) dataset. The clothes simulated by the extended position based dynamics (XPBD) algorithm realized fast and realistic modeling.
by Qi He.
S.M.
S.M. Massachusetts Institute of Technology, Department of Mechanical Engineering
59 pages
eng
Massachusetts Institute of Technology
MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.
http://dspace.mit.edu/handle/1721.1/7582
Mechanical Engineering.
3D reconstruction of human body via machine learning
3 dimensional reconstruction of human body via machine learning
Three-dimensional reconstruction of human body via machine learning
Thesis
application/pdf
2020-09-03T17:49:51Z
Publication
Master
MechE
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="f064e86a-3019-441a-9360-0941c7425955">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>3D reconstruction of human body via machine learning</Title>
<Subtitle>3 dimensional reconstruction of human body via machine learning</Subtitle>
<Subtitle>Three-dimensional reconstruction of human body via machine learning</Subtitle>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2020</PublicationDate>
<Authors>
<Author>
<DisplayName>Hi, Qi,S.M.Massachusetts Institute of Technology.</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Mechanical Engineering.</Keyword>
<Abstract>Three-dimensional (3D) reconstruction and modeling of the human body and garments from images is a central open problem in computer vision, yet remains a challenge using machine learning techniques. We proposed a framework to generate the realistic 3D human from a single RGB image via machine learning. The framework is composed of an end-to-end 3D reconstruction neural net with a skinned multi-person linear model (SMPL) model by the generative adversarial networks (GANs). The 3D facial reconstruction used the morphable facial model by principal component analysis (PCA) and the LS3D-W database. The 3D garments are reconstructed by the multi-garment net (MGN) to generate UV-mapping and remapped into the human model with motion transferred by archive of motion capture as surface shapes (AMASS) dataset. The clothes simulated by the extended position based dynamics (XPBD) algorithm realized fast and realistic modeling.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>