{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/119694"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/119694","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Generative adversarial modeling of 3D shapes","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_html":"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_has_math":false,"creators":["Zhang, Chengkai, M. Eng. Massachusetts Institute of Technology"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["Joshua B. Tenenbaum."],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018","date_published":"2018","updated_at":"2026-07-22T22:21:44Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["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."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/119694","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Joshua B. Tenenbaum."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Zhang, Chengkai, M. Eng. Massachusetts Institute of Technology"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2018-12-18T19:46:06Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2018-12-18T19:46:06Z"]},{"key":"dc:date.issued","label":"Date","values":["2018"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["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."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/119694"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["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)."]},{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M. Eng."]},{"key":"dc:title","label":"Title","values":["Generative adversarial modeling of 3D shapes"]}]}],"canonical_facts":{"dc:contributor.advisor":["Joshua B. Tenenbaum."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Zhang, Chengkai, M. Eng. Massachusetts Institute of Technology"],"dc:date.accessioned":["2018-12-18T19:46:06Z"],"dc:date.available":["2018-12-18T19:46:06Z"],"dc:date.issued":["2018"],"dc:description":["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)."],"dc:description.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."],"dc:description.degree":["M. Eng."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/119694"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["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."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Generative adversarial modeling of 3D shapes"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:44Z"}