{"id":{"repo_id":"cornell","oai_identifier":"oai:ecommons.cornell.edu:1813/114792"},"canonical_url":"https://search.ndltd.org/etd/cornell/oai:ecommons.cornell.edu:1813/114792","repository":{"repo_id":"cornell","name":"Cornell University","base_url":"https://ecommons.cornell.edu/server/oai/request"},"display":{"title":"Modeling the 3D World and its Motion","abstract":"Human visual systems have the remarkable ability to perceive the physical environment, providing a foundation for intelligent behaviors like navigation and interaction. To enhance artificial intelligence, one of the most crucial challenges is to improve machines' ability to perceive and model the dynamic 3D world from images and videos. This ability not only forms a fundamental basis for advanced intelligence but also enables numerous real-world applications like augmented reality (AR), virtual reality (VR), and content creation. In this thesis, my main focus is on developing algorithms that enhance machines' understanding and modeling of geometry and motion using everyday photos and videos. I first consider static scenes, where I tackle the problem of computing more accurate correspondences between image pairs, which serve as a crucial foundation for improving the estimation of camera poses and scene structure. Additionally, I propose a generalizable approach to effectively model the dense geometry and appearance of static scenes for view synthesis. Shifting to dynamic scenes, I study how to represent moving 3D scenes from the simple case of two views, and explore methods to model the dense and complete motion from video sequences.","abstract_html":"Human visual systems have the remarkable ability to perceive the physical environment, providing a foundation for intelligent behaviors like navigation and interaction. To enhance artificial intelligence, one of the most crucial challenges is to improve machines&#x27; ability to perceive and model the dynamic 3D world from images and videos. This ability not only forms a fundamental basis for advanced intelligence but also enables numerous real-world applications like augmented reality (AR), virtual reality (VR), and content creation. In this thesis, my main focus is on developing algorithms that enhance machines&#x27; understanding and modeling of geometry and motion using everyday photos and videos. I first consider static scenes, where I tackle the problem of computing more accurate correspondences between image pairs, which serve as a crucial foundation for improving the estimation of camera poses and scene structure. Additionally, I propose a generalizable approach to effectively model the dense geometry and appearance of static scenes for view synthesis. Shifting to dynamic scenes, I study how to represent moving 3D scenes from the simple case of two views, and explore methods to model the dense and complete motion from video sequences.","abstract_has_math":false,"creators":["Wang, Qianqian"],"institution":"Cornell University","degree_name":"Ph. D., Computer Science","degree_level":"Doctor of Philosophy","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":["Snavely, Keith"],"committee_members":["Hariharan, Bharath","Belongie, Serge","Zhang, Cheng"],"year":2023,"date_issued":"2023-08","date_published":"2023-08","updated_at":"2026-11-19T03:11:13Z","subjects":["3D Reconstruction","Image-Based Rendering","Motion Estimation","Novel View Synthesis"],"languages":["en"],"rights":["Attribution-ShareAlike 4.0 International"],"rights_urls":["https://creativecommons.org/licenses/by-sa/4.0/"],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/a07d-qc66"],"render_values":[{"text":"https://doi.org/10.7298/a07d-qc66","href":"https://doi.org/10.7298/a07d-qc66","code":true}]},{"key":"dc:identifier.bibid","label":"Dc Identifier Bibid","values":["16219317"],"render_values":[{"text":"16219317","href":null,"code":true}]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 13868","ProQuest Publication ID: 30574757"],"render_values":[{"text":"ProQuest Submission ID: 13868","href":null,"code":true},{"text":"ProQuest Publication ID: 30574757","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1813/114792","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/1813/114792","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://ecommons.cornell.edu/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aecommons.cornell.edu%3A1813%2F114792","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.chair","label":"Chair","values":["Snavely, Keith"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Hariharan, Bharath","Belongie, Serge","Zhang, Cheng"]},{"key":"dc:creator","label":"Author","values":["Wang, Qianqian"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-04-05T18:48:19Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-04-05T18:48:19Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-08"]},{"key":"dc:relation.uri","label":"Dc Relation URI","values":["https://newcatalog.library.cornell.edu/catalog/16219317"]},{"key":"dc:type","label":"Dc Type","values":["dissertation or thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctor of Philosophy"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph. D., Computer Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Cornell University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["3D Reconstruction","Image-Based Rendering","Motion Estimation","Novel View Synthesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution-ShareAlike 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-sa/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.bibid","label":"Dc Identifier Bibid","values":["16219317"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/a07d-qc66"]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 13868","ProQuest Publication ID: 30574757"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1813/114792"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"cerif:openaire","label":"Cerif Openaire","values":["<Publication xmlns=\"https://www.openaire.eu/cerif-profile/1.1/\" id=\"26f9645f-d7f1-449c-8aaf-42bea7c451b4\"> <Type xmlns=\"https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types\">http://purl.org/coar/resource_type/c_1843</Type> <Language>en</Language> <Title>Modeling the 3D World and its Motion</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2023-08</PublicationDate> <DOI>https://doi.org/10.7298/a07d-qc66</DOI> <Authors> <Author> <DisplayName>Wang, Qianqian</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <OrgUnit /> </Publisher> </Publishers> <License>https://creativecommons.org/licenses/by-sa/4.0/</License> <Keyword>3D Reconstruction</Keyword> <Keyword>Image-Based Rendering</Keyword> <Keyword>Motion Estimation</Keyword> <Keyword>Novel View Synthesis</Keyword> <Abstract>Human visual systems have the remarkable ability to perceive the physical environment, providing a foundation for intelligent behaviors like navigation and interaction. To enhance artificial intelligence, one of the most crucial challenges is to improve machines' ability to perceive and model the dynamic 3D world from images and videos. This ability not only forms a fundamental basis for advanced intelligence but also enables numerous real-world applications like augmented reality (AR), virtual reality (VR), and content creation. In this thesis, my main focus is on developing algorithms that enhance machines' understanding and modeling of geometry and motion using everyday photos and videos. I first consider static scenes, where I tackle the problem of computing more accurate correspondences between image pairs, which serve as a crucial foundation for improving the estimation of camera poses and scene structure. Additionally, I propose a generalizable approach to effectively model the dense geometry and appearance of static scenes for view synthesis. Shifting to dynamic scenes, I study how to represent moving 3D scenes from the simple case of two views, and explore methods to model the dense and complete motion from video sequences.</Abstract> <Access xmlns=\"http://purl.org/coar/access_right\" > </Access> </Publication>"]},{"key":"cris:virtual.author","label":"Cris Virtual Author","values":["Wang, Qianqian"]},{"key":"cris:virtualsource.collection","label":"Cris Virtualsource Collection","values":["5893a6ea-7af3-41d7-abc6-04bcd26ab5df"]},{"key":"dc:description","label":"Description","values":["168 pages","Supplemental file(s) description: Supplementary video for Chapter 5, Supplementary video for Chapter 3, Supplementary video for Chapter 4."]},{"key":"dc:description.abstract","label":"Abstract","values":["Human visual systems have the remarkable ability to perceive the physical environment, providing a foundation for intelligent behaviors like navigation and interaction. To enhance artificial intelligence, one of the most crucial challenges is to improve machines' ability to perceive and model the dynamic 3D world from images and videos. This ability not only forms a fundamental basis for advanced intelligence but also enables numerous real-world applications like augmented reality (AR), virtual reality (VR), and content creation. In this thesis, my main focus is on developing algorithms that enhance machines' understanding and modeling of geometry and motion using everyday photos and videos. I first consider static scenes, where I tackle the problem of computing more accurate correspondences between image pairs, which serve as a crucial foundation for improving the estimation of camera poses and scene structure. Additionally, I propose a generalizable approach to effectively model the dense geometry and appearance of static scenes for view synthesis. Shifting to dynamic scenes, I study how to represent moving 3D scenes from the simple case of two views, and explore methods to model the dense and complete motion from video sequences."]},{"key":"dc:description.collection","label":"Dc Description Collection","values":["Cornell Theses and Dissertations"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf","video/mpeg4","application/zip"]},{"key":"dcterms:license","label":"Dcterms License","values":["https://hdl.handle.net/1813/59810.2"]},{"key":"dc:title","label":"Title","values":["Modeling the 3D World and its Motion"]},{"key":"dspace:entity.type","label":"Dspace Entity Type","values":["Publication"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"cerif:openaire":["<Publication xmlns=\"https://www.openaire.eu/cerif-profile/1.1/\" id=\"26f9645f-d7f1-449c-8aaf-42bea7c451b4\"> <Type xmlns=\"https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types\">http://purl.org/coar/resource_type/c_1843</Type> <Language>en</Language> <Title>Modeling the 3D World and its Motion</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2023-08</PublicationDate> <DOI>https://doi.org/10.7298/a07d-qc66</DOI> <Authors> <Author> <DisplayName>Wang, Qianqian</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <OrgUnit /> </Publisher> </Publishers> <License>https://creativecommons.org/licenses/by-sa/4.0/</License> <Keyword>3D Reconstruction</Keyword> <Keyword>Image-Based Rendering</Keyword> <Keyword>Motion Estimation</Keyword> <Keyword>Novel View Synthesis</Keyword> <Abstract>Human visual systems have the remarkable ability to perceive the physical environment, providing a foundation for intelligent behaviors like navigation and interaction. To enhance artificial intelligence, one of the most crucial challenges is to improve machines' ability to perceive and model the dynamic 3D world from images and videos. This ability not only forms a fundamental basis for advanced intelligence but also enables numerous real-world applications like augmented reality (AR), virtual reality (VR), and content creation. In this thesis, my main focus is on developing algorithms that enhance machines' understanding and modeling of geometry and motion using everyday photos and videos. I first consider static scenes, where I tackle the problem of computing more accurate correspondences between image pairs, which serve as a crucial foundation for improving the estimation of camera poses and scene structure. Additionally, I propose a generalizable approach to effectively model the dense geometry and appearance of static scenes for view synthesis. Shifting to dynamic scenes, I study how to represent moving 3D scenes from the simple case of two views, and explore methods to model the dense and complete motion from video sequences.</Abstract> <Access xmlns=\"http://purl.org/coar/access_right\" > </Access> </Publication>"],"cris:virtual.author":["Wang, Qianqian"],"cris:virtualsource.collection":["5893a6ea-7af3-41d7-abc6-04bcd26ab5df"],"dc:contributor.chair":["Snavely, Keith"],"dc:contributor.committeemember":["Hariharan, Bharath","Belongie, Serge","Zhang, Cheng"],"dc:creator":["Wang, Qianqian"],"dc:date.accessioned":["2024-04-05T18:48:19Z"],"dc:date.available":["2024-04-05T18:48:19Z"],"dc:date.issued":["2023-08"],"dc:description":["168 pages","Supplemental file(s) description: Supplementary video for Chapter 5, Supplementary video for Chapter 3, Supplementary video for Chapter 4."],"dc:description.abstract":["Human visual systems have the remarkable ability to perceive the physical environment, providing a foundation for intelligent behaviors like navigation and interaction. To enhance artificial intelligence, one of the most crucial challenges is to improve machines' ability to perceive and model the dynamic 3D world from images and videos. This ability not only forms a fundamental basis for advanced intelligence but also enables numerous real-world applications like augmented reality (AR), virtual reality (VR), and content creation. In this thesis, my main focus is on developing algorithms that enhance machines' understanding and modeling of geometry and motion using everyday photos and videos. I first consider static scenes, where I tackle the problem of computing more accurate correspondences between image pairs, which serve as a crucial foundation for improving the estimation of camera poses and scene structure. Additionally, I propose a generalizable approach to effectively model the dense geometry and appearance of static scenes for view synthesis. Shifting to dynamic scenes, I study how to represent moving 3D scenes from the simple case of two views, and explore methods to model the dense and complete motion from video sequences."],"dc:description.collection":["Cornell Theses and Dissertations"],"dc:format.mimetype":["application/pdf","video/mpeg4","application/zip"],"dc:identifier.bibid":["16219317"],"dc:identifier.doi":["https://doi.org/10.7298/a07d-qc66"],"dc:identifier.other":["ProQuest Submission ID: 13868","ProQuest Publication ID: 30574757"],"dc:identifier.uri":["https://hdl.handle.net/1813/114792"],"dc:language.iso":["en"],"dc:relation.uri":["https://newcatalog.library.cornell.edu/catalog/16219317"],"dc:rights":["Attribution-ShareAlike 4.0 International"],"dc:rights.uri":["https://creativecommons.org/licenses/by-sa/4.0/"],"dc:subject":["3D Reconstruction","Image-Based Rendering","Motion Estimation","Novel View Synthesis"],"dcterms:license":["https://hdl.handle.net/1813/59810.2"],"dc:title":["Modeling the 3D World and its Motion"],"dc:type":["dissertation or thesis"],"dspace:entity.type":["Publication"],"others:access_status":["open.access"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Doctor of Philosophy"],"thesis:degree_name":["Ph. D., Computer Science"],"thesis:institution_name":["Cornell University"]},"updated_at":"2026-11-19T03:11:13Z"}