{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/127176"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/127176","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Harnessing data priors to mitigate 3D data scarcity","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","abstract_has_math":false,"creators":["Zhao, Xiaoming"],"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","Hoiem, Derek W","Wang, Shenlong","Colburn, Alex"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-11-04","date_published":"2024-11-04","updated_at":"2026-07-22T22:25:03Z","subjects":["3d Computer Vision","Novel View Synthesis","Dynamic Novel View Synthesis","Generative Adversarial Network","Diffusion Model","3d Relighting"],"languages":["en","eng"],"rights":["Copyright 2024 Xiaoming Zhao"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/127176","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Schwing, Alexander Gerhard","Hoiem, Derek W","Wang, Shenlong","Colburn, Alex"]},{"key":"dc:creator","label":"Author","values":["Zhao, Xiaoming"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-11-04","2024-12"]},{"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":["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":["3d Computer Vision","Novel View Synthesis","Dynamic Novel View Synthesis","Generative Adversarial Network","Diffusion Model","3d Relighting"]}]},{"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 2024 Xiaoming Zhao"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/127176"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","The student, Xiaoming Zhao, accepted the attached license on 2024-10-31 at 17:29.","The student, Xiaoming Zhao, submitted this Dissertation for approval on 2024-10-31 at 17:39.","This Dissertation was approved for publication on 2024-11-04 at 14:46.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21285 on 2025-03-28 at 14:25:22","Recently, we have witnessed remarkable advances in various fields related to machine learning and artificial intelligence, e.g., the rise of Large Language Models (LLMs) for natural language processing and diffusion models for visual content generation. Alongside improvements in algorithm design, the ability to train models on massive data has undoubtedly been a cornerstone of such progress. However, not all fields or tasks have the privilege of obtaining data of a similar scale. This naturally raises the question: how can we address the challenge of data scarcity in areas where large datasets are unavailable? In this dissertation, we study this challenge in the context of 3D computer vision and demonstrate how harnessing data priors from various domains can help mitigate 3D data scarcity. We begin by focusing on the task of dynamic view synthesis. By incorporating various data priors, e.g., those from a pre-trained static view synthesis model, we develop a system that is capable of producing high-quality free-viewpoint and free-time rendering from a monocular video without access to large-scale real-world multiview 4D (3D + time) data. In the domain of category-specific 3D content generation, we propose to leverage data priors from a pre-trained 2D Generative Adversarial Network (GAN), enabling us to obtain a 3D-aware GAN model very efficiently without relying on real-world multiview 3D data. Additionally, we utilize data priors from a pre-trained text-to-image diffusion model to tackle the task of 3D lighting, a new paradigm that outperforms many state-of-the-art inverse rendering approaches, without the need for extensive real-world multiview 3D relighting data. Finally, we conclude this dissertation with promising future directions."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Harnessing data priors to mitigate 3D data scarcity"]}]}],"canonical_facts":{"dc:contributor":["Schwing, Alexander Gerhard","Hoiem, Derek W","Wang, Shenlong","Colburn, Alex"],"dc:creator":["Zhao, Xiaoming"],"dc:date":["2024-11-04","2024-12"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","The student, Xiaoming Zhao, accepted the attached license on 2024-10-31 at 17:29.","The student, Xiaoming Zhao, submitted this Dissertation for approval on 2024-10-31 at 17:39.","This Dissertation was approved for publication on 2024-11-04 at 14:46.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21285 on 2025-03-28 at 14:25:22","Recently, we have witnessed remarkable advances in various fields related to machine learning and artificial intelligence, e.g., the rise of Large Language Models (LLMs) for natural language processing and diffusion models for visual content generation. Alongside improvements in algorithm design, the ability to train models on massive data has undoubtedly been a cornerstone of such progress. However, not all fields or tasks have the privilege of obtaining data of a similar scale. This naturally raises the question: how can we address the challenge of data scarcity in areas where large datasets are unavailable? In this dissertation, we study this challenge in the context of 3D computer vision and demonstrate how harnessing data priors from various domains can help mitigate 3D data scarcity. We begin by focusing on the task of dynamic view synthesis. By incorporating various data priors, e.g., those from a pre-trained static view synthesis model, we develop a system that is capable of producing high-quality free-viewpoint and free-time rendering from a monocular video without access to large-scale real-world multiview 4D (3D + time) data. In the domain of category-specific 3D content generation, we propose to leverage data priors from a pre-trained 2D Generative Adversarial Network (GAN), enabling us to obtain a 3D-aware GAN model very efficiently without relying on real-world multiview 3D data. Additionally, we utilize data priors from a pre-trained text-to-image diffusion model to tackle the task of 3D lighting, a new paradigm that outperforms many state-of-the-art inverse rendering approaches, without the need for extensive real-world multiview 3D relighting data. Finally, we conclude this dissertation with promising future directions."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/127176"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Xiaoming Zhao"],"dc:subject":["3d Computer Vision","Novel View Synthesis","Dynamic Novel View Synthesis","Generative Adversarial Network","Diffusion Model","3d Relighting"],"dc:title":["Harnessing data priors to mitigate 3D data scarcity"],"dc:type":["text","Thesis"],"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":"2026-07-22T22:25:03Z"}