{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108048"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108048","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Training large-scale video generative adversarial networks for high quality video synthesis","abstract":"Video synthesis using deep learning methods is an important yet challenging task for the computer vision community. Generative Adversarial Networks have been proved effective for generating high fidelity photo-realistic images. Recently, many video synthesis models achieve high fidelity and resolution samples by carrying the success of Generative Adversarial Networks to the field of video synthesis. However, it can be challenging to train large-scale Generative Adversarial Networks as they often require enormous computing resources and a long training period. We found it necessary to put together a clear and in-depth guideline for researchers who are interested in training large-scale video Generative Adversarial Networks in the future. In this thesis, we aim to find effective and efficient ways to implement and train large-scale video Generative Adversarial Networks for high quality video generation. We evaluate different implement choices as well as training details and give quantitative analysis.","abstract_html":"Video synthesis using deep learning methods is an important yet challenging task for the computer vision community. Generative Adversarial Networks have been proved effective for generating high fidelity photo-realistic images. Recently, many video synthesis models achieve high fidelity and resolution samples by carrying the success of Generative Adversarial Networks to the field of video synthesis. However, it can be challenging to train large-scale Generative Adversarial Networks as they often require enormous computing resources and a long training period. We found it necessary to put together a clear and in-depth guideline for researchers who are interested in training large-scale video Generative Adversarial Networks in the future. In this thesis, we aim to find effective and efficient ways to implement and train large-scale video Generative Adversarial Networks for high quality video generation. We evaluate different implement choices as well as training details and give quantitative analysis.","abstract_has_math":false,"creators":["Du, Xiaodan"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Lazebnik, Svetlana"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-08-26T21:58:05Z","date_published":"2020-08-26T21:58:05Z","updated_at":"2026-07-22T22:24:47Z","subjects":["Generative Adversarial Networks","video synthesis","computer vision"],"languages":["en"],"rights":["Copyright 2020 Xiaodan Du"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108048","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lazebnik, Svetlana"]},{"key":"dc:creator","label":"Author","values":["Du, Xiaodan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-08-26T21:58:05Z","2020-05-13","2020-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Generative Adversarial Networks","video synthesis","computer vision"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 Xiaodan Du"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108048"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Video synthesis using deep learning methods is an important yet challenging task for the computer vision community. Generative Adversarial Networks have been proved effective for generating high fidelity photo-realistic images. Recently, many video synthesis models achieve high fidelity and resolution samples by carrying the success of Generative Adversarial Networks to the field of video synthesis. However, it can be challenging to train large-scale Generative Adversarial Networks as they often require enormous computing resources and a long training period. We found it necessary to put together a clear and in-depth guideline for researchers who are interested in training large-scale video Generative Adversarial Networks in the future. In this thesis, we aim to find effective and efficient ways to implement and train large-scale video Generative Adversarial Networks for high quality video generation. We evaluate different implement choices as well as training details and give quantitative analysis.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Xiaodan Du, accepted the attached license on 2020-05-12 at 12:41.","The student, Xiaodan Du, submitted this Thesis for approval on 2020-05-12 at 12:49.","This Thesis was approved for publication on 2020-05-13 at 08:56.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15353 on 2020-08-25 at 17:14:21","Made available in DSpace on 2020-08-26T21:58:05Z (GMT). No. of bitstreams: 2 DU-THESIS-2020.pdf: 6448005 bytes, checksum: a4920a59447c89a20391dc9c8030504e (MD5) LICENSE.txt: 4207 bytes, checksum: 89616524dbd287e002cd5f30c9b68e7c (MD5) Previous issue date: 2020-05-13"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Training large-scale video generative adversarial networks for high quality video synthesis"]}]}],"canonical_facts":{"dc:contributor":["Lazebnik, Svetlana"],"dc:creator":["Du, Xiaodan"],"dc:date":["2020-08-26T21:58:05Z","2020-05-13","2020-05"],"dc:description":["Video synthesis using deep learning methods is an important yet challenging task for the computer vision community. Generative Adversarial Networks have been proved effective for generating high fidelity photo-realistic images. Recently, many video synthesis models achieve high fidelity and resolution samples by carrying the success of Generative Adversarial Networks to the field of video synthesis. However, it can be challenging to train large-scale Generative Adversarial Networks as they often require enormous computing resources and a long training period. We found it necessary to put together a clear and in-depth guideline for researchers who are interested in training large-scale video Generative Adversarial Networks in the future. In this thesis, we aim to find effective and efficient ways to implement and train large-scale video Generative Adversarial Networks for high quality video generation. We evaluate different implement choices as well as training details and give quantitative analysis.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Xiaodan Du, accepted the attached license on 2020-05-12 at 12:41.","The student, Xiaodan Du, submitted this Thesis for approval on 2020-05-12 at 12:49.","This Thesis was approved for publication on 2020-05-13 at 08:56.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15353 on 2020-08-25 at 17:14:21","Made available in DSpace on 2020-08-26T21:58:05Z (GMT). No. of bitstreams: 2 DU-THESIS-2020.pdf: 6448005 bytes, checksum: a4920a59447c89a20391dc9c8030504e (MD5) LICENSE.txt: 4207 bytes, checksum: 89616524dbd287e002cd5f30c9b68e7c (MD5) Previous issue date: 2020-05-13"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108048"],"dc:language":["en"],"dc:rights":["Copyright 2020 Xiaodan Du"],"dc:subject":["Generative Adversarial Networks","video synthesis","computer vision"],"dc:title":["Training large-scale video generative adversarial networks for high quality video synthesis"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:47Z"}