{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108020"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108020","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Unsupervised monocular depth estimation: Learning to generalize","abstract":"Models for unsupervised monocular depth estimation (MDE) have gained much attention due to recent breakthroughs and the ability to train with unlabeled data. Despite the state-of-the-art methods performing well on depth prediction benchmarks, certain artifacts and their performance compared to their supervised counterparts make them less favorable in certain domains. This thesis analyzes these models and presents a set of methods for improvement which can be applied in the training process. Recent papers in unsupervised MDE focus on increasing performance metrics on the KITTI benchmark. We show that the results from these methods can be further improved by (i) providing synthetic training data via the game engine Grand Theft Auto V (GTAV) and (ii) applying data augmentation techniques that are consistent with the camera intrinsic parameters of the model.","abstract_html":"Models for unsupervised monocular depth estimation (MDE) have gained much attention due to recent breakthroughs and the ability to train with unlabeled data. Despite the state-of-the-art methods performing well on depth prediction benchmarks, certain artifacts and their performance compared to their supervised counterparts make them less favorable in certain domains. This thesis analyzes these models and presents a set of methods for improvement which can be applied in the training process. Recent papers in unsupervised MDE focus on increasing performance metrics on the KITTI benchmark. We show that the results from these methods can be further improved by (i) providing synthetic training data via the game engine Grand Theft Auto V (GTAV) and (ii) applying data augmentation techniques that are consistent with the camera intrinsic parameters of the model.","abstract_has_math":false,"creators":["Gonzales, Daniel"],"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":["Do, Minh"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-08-26T21:57:59Z","date_published":"2020-08-26T21:57:59Z","updated_at":"2026-07-22T22:24:47Z","subjects":["Monocular","Depth"],"languages":["en"],"rights":["Copyright 2020 Daniel Gonzales"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108020","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Do, Minh"]},{"key":"dc:creator","label":"Author","values":["Gonzales, Daniel"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-08-26T21:57:59Z","2020-05-11","2020-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"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":["Monocular","Depth"]}]},{"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 Daniel Gonzales"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108020"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Models for unsupervised monocular depth estimation (MDE) have gained much attention due to recent breakthroughs and the ability to train with unlabeled data. Despite the state-of-the-art methods performing well on depth prediction benchmarks, certain artifacts and their performance compared to their supervised counterparts make them less favorable in certain domains. This thesis analyzes these models and presents a set of methods for improvement which can be applied in the training process. Recent papers in unsupervised MDE focus on increasing performance metrics on the KITTI benchmark. We show that the results from these methods can be further improved by (i) providing synthetic training data via the game engine Grand Theft Auto V (GTAV) and (ii) applying data augmentation techniques that are consistent with the camera intrinsic parameters of the model.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Daniel Gonzales, accepted the attached license on 2020-05-08 at 14:53.","The student, Daniel Gonzales, submitted this Thesis for approval on 2020-05-08 at 14:58.","This Thesis was approved for publication on 2020-05-11 at 14:04.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15300 on 2020-08-25 at 17:13:35","Made available in DSpace on 2020-08-26T21:57:59Z (GMT). No. of bitstreams: 2 GONZALES-THESIS-2020.pdf: 12032216 bytes, checksum: 8a046a70995b0e0ac7fd05ff1171b5fe (MD5) LICENSE.txt: 4212 bytes, checksum: 953825c45af3464445f731720bc04437 (MD5) Previous issue date: 2020-05-11"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Unsupervised monocular depth estimation: Learning to generalize"]}]}],"canonical_facts":{"dc:contributor":["Do, Minh"],"dc:creator":["Gonzales, Daniel"],"dc:date":["2020-08-26T21:57:59Z","2020-05-11","2020-05"],"dc:description":["Models for unsupervised monocular depth estimation (MDE) have gained much attention due to recent breakthroughs and the ability to train with unlabeled data. Despite the state-of-the-art methods performing well on depth prediction benchmarks, certain artifacts and their performance compared to their supervised counterparts make them less favorable in certain domains. This thesis analyzes these models and presents a set of methods for improvement which can be applied in the training process. Recent papers in unsupervised MDE focus on increasing performance metrics on the KITTI benchmark. We show that the results from these methods can be further improved by (i) providing synthetic training data via the game engine Grand Theft Auto V (GTAV) and (ii) applying data augmentation techniques that are consistent with the camera intrinsic parameters of the model.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Daniel Gonzales, accepted the attached license on 2020-05-08 at 14:53.","The student, Daniel Gonzales, submitted this Thesis for approval on 2020-05-08 at 14:58.","This Thesis was approved for publication on 2020-05-11 at 14:04.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15300 on 2020-08-25 at 17:13:35","Made available in DSpace on 2020-08-26T21:57:59Z (GMT). No. of bitstreams: 2 GONZALES-THESIS-2020.pdf: 12032216 bytes, checksum: 8a046a70995b0e0ac7fd05ff1171b5fe (MD5) LICENSE.txt: 4212 bytes, checksum: 953825c45af3464445f731720bc04437 (MD5) Previous issue date: 2020-05-11"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108020"],"dc:language":["en"],"dc:rights":["Copyright 2020 Daniel Gonzales"],"dc:subject":["Monocular","Depth"],"dc:title":["Unsupervised monocular depth estimation: Learning to generalize"],"dc:type":["text","Thesis"],"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"}