2026-09-19T01:18:36Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1196942026-06-06T00:55:03Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Joshua B. Tenenbaum. Zhang, Chengkai, M. Eng. Massachusetts Institute of Technology Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2018-12-18T19:46:06Z 2018-12-18T19:46:06Z 2018 2018 http://hdl.handle.net/1721.1/119694 1078150040 Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 53-59). Given a 3D shape, humans are capable of telling whether it looks natural. This shape priors, namely the perception of whether a shape looks realistic, are formed over years of our interactions with surrounding 3D objects, and go beyond simple definition of objects. In this thesis, we propose two models, 3D Generative Adversarial Network and ShapeHD, to learn shape priors from existing 3D shapes via generative-adversarial modeling, pushing the limits of shape generation, single-view shape completion and reconstruction. For shape generation, we demonstrate that our 3D-GAN generates high-quality 3D objects, and our unsupervisedly learned features achieve impressive performance on 3D object recognition, comparable with those of supervised learning methods; for single-view shape completion and reconstruction, we show that ShapeHD recovers fine details for 3D shapes, and outperforms state-of-the-art by a large margin on both tasks. by Chengkai Zhang. M.Eng. 59 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Generative adversarial modeling of 3D shapes Generative adversarial modeling of three- D shapes Generative adversarial modeling of three-dimensional shapes Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="8ca604fa-3e67-462c-bdf7-615e2ba41c6e"> <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>Generative adversarial modeling of 3D shapes</Title> <Subtitle>Generative adversarial modeling of three- D shapes</Subtitle> <Subtitle>Generative adversarial modeling of three-dimensional shapes</Subtitle> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2018</PublicationDate> <Authors> <Author> <DisplayName>Zhang, Chengkai, M. Eng. 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>Electrical Engineering and Computer Science.</Keyword> <Abstract>Given a 3D shape, humans are capable of telling whether it looks natural. This shape priors, namely the perception of whether a shape looks realistic, are formed over years of our interactions with surrounding 3D objects, and go beyond simple definition of objects. In this thesis, we propose two models, 3D Generative Adversarial Network and ShapeHD, to learn shape priors from existing 3D shapes via generative-adversarial modeling, pushing the limits of shape generation, single-view shape completion and reconstruction. For shape generation, we demonstrate that our 3D-GAN generates high-quality 3D objects, and our unsupervisedly learned features achieve impressive performance on 3D object recognition, comparable with those of supervised learning methods; for single-view shape completion and reconstruction, we show that ShapeHD recovers fine details for 3D shapes, and outperforms state-of-the-art by a large margin on both tasks.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>