3D reconstruction of human body via machine learning
Name
1191844129-MIT.pdf
Size
3.21 MB
Format
Adobe PDF
Checksum (MD5)
04cfef72eb3a2100f2744ead11910f50
Author(s)
Hi, Qi,S.M.Massachusetts Institute of Technology.
Advisor(s)
Ju Li.
Alternative Title
3 dimensional reconstruction of human body via machine learning
Three-dimensional reconstruction of human body via machine learning
Date Issued
2020
Publisher
Massachusetts Institute of Technology
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.
Description
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).
Subjects
Mechanical Engineering.
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
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.
Persistent DSpace Link
