{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/106427"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/106427","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Analysis of loss functions in XVAE-GAN: A novel two-view image generation network","abstract":"DSpace SAF Submission Ingestion Package generated from Vireo submission #14457 on 2020-02-28 at 17:35:35","abstract_html":"DSpace SAF Submission Ingestion Package generated from Vireo submission #14457 on 2020-02-28 at 17:35:35","abstract_has_math":false,"creators":["Qin, Zhen"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Schwing, Alexander"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-03-02T22:38:37Z","date_published":"2020-03-02T22:38:37Z","updated_at":"2026-07-22T22:24:47Z","subjects":["GAN","Computer Vision","VAE","Generative Model","Representation Learning","Image-to-Image Translation","Deep Learning"],"languages":["en"],"rights":["Copyright 2019 Zhen Qin"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/106427","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Schwing, Alexander"]},{"key":"dc:creator","label":"Author","values":["Qin, Zhen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-03-02T22:38:37Z","2022-03-03T10:15:08Z","2019-12-09","2019-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"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":["GAN","Computer Vision","VAE","Generative Model","Representation Learning","Image-to-Image Translation","Deep Learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2019 Zhen Qin"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/106427"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["DSpace SAF Submission Ingestion Package generated from Vireo submission #14457 on 2020-02-28 at 17:35:35","Made available in DSpace on 2020-03-02T22:38:37Z (GMT). No. of bitstreams: 2 QIN-THESIS-2019.pdf: 2042318 bytes, checksum: 463d56ebc7eef37c437038b57fd23a2e (MD5) LICENSE.txt: 4205 bytes, checksum: 285fef54c2f3e2425377cd46d2dbce6e (MD5) Previous issue date: 2019-12-09","Embargo set by: Seth Robbins for item 113971 Lift date: 2022-03-02T22:39:04Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 113971 on 2022-03-03T10:15:08Z.","Generating novel views from 2D images has been a popular topic in computer vision given its usefulness in a wide range of applications. However, the task is challenging due to its ill-posed nature. Recent attempts have been extensively focusing on modeling the transition between different views as an image-to-image translation problem using deep neural networks inspired from the breakthroughs of novel generative models such as generative adversarial networks (GAN). However, very few if any existing works provide an insight on the relation between representations learned in the latent spaces from different views. To complement this missing aspect in the problem space, we introduce a novel two-stream network based on variational autoencoders and GANs (XVAE-GAN) as an attempt to disentangle common features shared between two views and private features distinctively belong to each view in a pairwise two-view image synthesis setting. This thesis presents a survey on existing works targeting on multi-view image synthesis problem, then introduces our newly proposed XVAE-GAN network in detail. The rest of the thesis is focused on ablation study investigating the impact of different loss functions on our proposed model by experimenting with three different applications: face image rotation, frontal/lateral chest X-ray image synthesis and ground/aerial street-view synthesis.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2021-12-01","The student, Zhen Qin, accepted the attached license on 2019-12-06 at 12:08.","The student, Zhen Qin, submitted this Thesis for approval on 2019-12-06 at 13:03.","This Thesis was approved for publication on 2019-12-09 at 09:04."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Analysis of loss functions in XVAE-GAN: A novel two-view image generation network"]}]}],"canonical_facts":{"dc:contributor":["Schwing, Alexander"],"dc:creator":["Qin, Zhen"],"dc:date":["2020-03-02T22:38:37Z","2022-03-03T10:15:08Z","2019-12-09","2019-12"],"dc:description":["DSpace SAF Submission Ingestion Package generated from Vireo submission #14457 on 2020-02-28 at 17:35:35","Made available in DSpace on 2020-03-02T22:38:37Z (GMT). No. of bitstreams: 2 QIN-THESIS-2019.pdf: 2042318 bytes, checksum: 463d56ebc7eef37c437038b57fd23a2e (MD5) LICENSE.txt: 4205 bytes, checksum: 285fef54c2f3e2425377cd46d2dbce6e (MD5) Previous issue date: 2019-12-09","Embargo set by: Seth Robbins for item 113971 Lift date: 2022-03-02T22:39:04Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 113971 on 2022-03-03T10:15:08Z.","Generating novel views from 2D images has been a popular topic in computer vision given its usefulness in a wide range of applications. However, the task is challenging due to its ill-posed nature. Recent attempts have been extensively focusing on modeling the transition between different views as an image-to-image translation problem using deep neural networks inspired from the breakthroughs of novel generative models such as generative adversarial networks (GAN). However, very few if any existing works provide an insight on the relation between representations learned in the latent spaces from different views. To complement this missing aspect in the problem space, we introduce a novel two-stream network based on variational autoencoders and GANs (XVAE-GAN) as an attempt to disentangle common features shared between two views and private features distinctively belong to each view in a pairwise two-view image synthesis setting. This thesis presents a survey on existing works targeting on multi-view image synthesis problem, then introduces our newly proposed XVAE-GAN network in detail. The rest of the thesis is focused on ablation study investigating the impact of different loss functions on our proposed model by experimenting with three different applications: face image rotation, frontal/lateral chest X-ray image synthesis and ground/aerial street-view synthesis.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2021-12-01","The student, Zhen Qin, accepted the attached license on 2019-12-06 at 12:08.","The student, Zhen Qin, submitted this Thesis for approval on 2019-12-06 at 13:03.","This Thesis was approved for publication on 2019-12-09 at 09:04."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/106427"],"dc:language":["en"],"dc:rights":["Copyright 2019 Zhen Qin"],"dc:subject":["GAN","Computer Vision","VAE","Generative Model","Representation Learning","Image-to-Image Translation","Deep Learning"],"dc:title":["Analysis of loss functions in XVAE-GAN: A novel two-view image generation network"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"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"}