{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/122204"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/122204","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Towards democratizing generation of 3D experiences","abstract":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2025-12-01","abstract_html":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2025-12-01","abstract_has_math":false,"creators":["Ren, Zhongzheng"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Schwing, Alexander Gerhard","Forsyth, David","Lazebnik, Svetlana","Hoiem, Derek","Agarwala, Aseem"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-12","date_published":"2023-12","updated_at":"2026-07-22T22:25:00Z","subjects":["Computer Vision","3d"],"languages":["en","eng"],"rights":["Copyright 2023 Zhongzheng Ren"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/122204","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Schwing, Alexander Gerhard","Forsyth, David","Lazebnik, Svetlana","Hoiem, Derek","Agarwala, Aseem"]},{"key":"dc:creator","label":"Author","values":["Ren, Zhongzheng"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-12","2023-11-27"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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":["Computer Vision","3d"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2023 Zhongzheng Ren"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/122204"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2025-12-01","The student, Zhongzheng Ren, accepted the attached license on 2023-11-22 at 07:37.","The student, Zhongzheng Ren, submitted this Dissertation for approval on 2023-11-22 at 08:04.","This Dissertation was approved for publication on 2023-11-27 at 11:28.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19840 on 2024-03-01 at 13:47:54","3D experiences offer a significantly more immersive platform for learning and entertainment when compared to 2D media, enabling a deeper understanding of complex real-world processes and fostering the creation of lasting memories. However, the conventional approach to generating such experiences is both labor-intensive and cost-prohibitive. Additionally, state-of-the-art deep learning solutions often encounter challenges in scaling due to the limited availability of large-scale 3D supervision. This limitation arises from the fact that while real-world 3D data is abundant, it is often sparsely annotated. In light of these challenges, this thesis aims to democratize the process of generating 3D experiences by exploring the following key research objectives: 1) Developing an innovative generation pipeline starting from recognizing 3D objects efficiently without relying on 3D labels. 2) Creating a class-agnostic approach for reconstructing dynamic objects from unstructured video data. 3) Investigating methods for manipulating and selecting 3D assets based solely on 2D user scribbles. Through these research efforts, this thesis seeks to pave the way for more accessible and cost-effective 3D content creation, with broader applications in fields such as science, entertainment, and beyond."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Towards democratizing generation of 3D experiences"]}]}],"canonical_facts":{"dc:contributor":["Schwing, Alexander Gerhard","Forsyth, David","Lazebnik, Svetlana","Hoiem, Derek","Agarwala, Aseem"],"dc:creator":["Ren, Zhongzheng"],"dc:date":["2023-12","2023-11-27"],"dc:description":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2025-12-01","The student, Zhongzheng Ren, accepted the attached license on 2023-11-22 at 07:37.","The student, Zhongzheng Ren, submitted this Dissertation for approval on 2023-11-22 at 08:04.","This Dissertation was approved for publication on 2023-11-27 at 11:28.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19840 on 2024-03-01 at 13:47:54","3D experiences offer a significantly more immersive platform for learning and entertainment when compared to 2D media, enabling a deeper understanding of complex real-world processes and fostering the creation of lasting memories. However, the conventional approach to generating such experiences is both labor-intensive and cost-prohibitive. Additionally, state-of-the-art deep learning solutions often encounter challenges in scaling due to the limited availability of large-scale 3D supervision. This limitation arises from the fact that while real-world 3D data is abundant, it is often sparsely annotated. In light of these challenges, this thesis aims to democratize the process of generating 3D experiences by exploring the following key research objectives: 1) Developing an innovative generation pipeline starting from recognizing 3D objects efficiently without relying on 3D labels. 2) Creating a class-agnostic approach for reconstructing dynamic objects from unstructured video data. 3) Investigating methods for manipulating and selecting 3D assets based solely on 2D user scribbles. Through these research efforts, this thesis seeks to pave the way for more accessible and cost-effective 3D content creation, with broader applications in fields such as science, entertainment, and beyond."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/122204"],"dc:language":["en","eng"],"dc:rights":["Copyright 2023 Zhongzheng Ren"],"dc:subject":["Computer Vision","3d"],"dc:title":["Towards democratizing generation of 3D experiences"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:00Z"}