{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/124287"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/124287","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Studies of lighting for dense prediction and generation in computer vision","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","abstract_has_math":false,"creators":["Soole, James"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Forsyth, David A"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:25:00Z","subjects":["Computer Vision","Artificial Intelligence","Deep Learning","Generative Ai","Intrinsics","Dense Prediction"],"languages":["en","eng"],"rights":["Copyright 2024 James Soole"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/124287","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Forsyth, David A"]},{"key":"dc:creator","label":"Author","values":["Soole, James"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-05","2024-04-25"]},{"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":["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":["Computer Vision","Artificial Intelligence","Deep Learning","Generative Ai","Intrinsics","Dense Prediction"]}]},{"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 James Soole"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/124287"]}]},{"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 2024-09-16 without embargo terms","The student, James Soole, accepted the attached license on 2024-04-15 at 14:19.","The student, James Soole, submitted this Thesis for approval on 2024-04-15 at 14:35.","This Thesis was approved for publication on 2024-04-25 at 14:27.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20415 on 2024-09-16 at 00:34:23","Modern dense prediction models do exceedingly well on benchmarks for the standard computer vision tasks of depth and normal estimation, object detection, and semantic segmentation. However, we show that the lighting in a scene has a significant effect on predictions, often producing inconsistent results for relit versions of the exact same scene. For surface normal prediction, we demonstrate that fine-tuning to enforce consistency under various lightings can mitigate this problem without sacrificing base accuracy of the pretrained model. Yet, such fine-tuning requires a dataset of relit scenes, which exist in limited quantity and are burdensome to produce. We therefore explore existing generative methods to create a synthetic relighting dataset, and propose our new method StyLitGAN. Based on StyleGAN architecture and the use of latent stylecode directions, StyLitGAN can realistically relight complex scenes without the need for labeled data. Fine-tuning a dense predictor with StyLitGAN images results in improvements comparable with that obtained by fine-tuning with true multi-illuminant images. We continue to investigate the effect of stylecode directions across different scenes, and show their use in producing desired results from reference images. We explore stylecode applications in explicitly-controllable scene lighting and uncover hints at their internal representation."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Studies of lighting for dense prediction and generation in computer vision"]}]}],"canonical_facts":{"dc:contributor":["Forsyth, David A"],"dc:creator":["Soole, James"],"dc:date":["2024-05","2024-04-25"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","The student, James Soole, accepted the attached license on 2024-04-15 at 14:19.","The student, James Soole, submitted this Thesis for approval on 2024-04-15 at 14:35.","This Thesis was approved for publication on 2024-04-25 at 14:27.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20415 on 2024-09-16 at 00:34:23","Modern dense prediction models do exceedingly well on benchmarks for the standard computer vision tasks of depth and normal estimation, object detection, and semantic segmentation. However, we show that the lighting in a scene has a significant effect on predictions, often producing inconsistent results for relit versions of the exact same scene. For surface normal prediction, we demonstrate that fine-tuning to enforce consistency under various lightings can mitigate this problem without sacrificing base accuracy of the pretrained model. Yet, such fine-tuning requires a dataset of relit scenes, which exist in limited quantity and are burdensome to produce. We therefore explore existing generative methods to create a synthetic relighting dataset, and propose our new method StyLitGAN. Based on StyleGAN architecture and the use of latent stylecode directions, StyLitGAN can realistically relight complex scenes without the need for labeled data. Fine-tuning a dense predictor with StyLitGAN images results in improvements comparable with that obtained by fine-tuning with true multi-illuminant images. We continue to investigate the effect of stylecode directions across different scenes, and show their use in producing desired results from reference images. We explore stylecode applications in explicitly-controllable scene lighting and uncover hints at their internal representation."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/124287"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 James Soole"],"dc:subject":["Computer Vision","Artificial Intelligence","Deep Learning","Generative Ai","Intrinsics","Dense Prediction"],"dc:title":["Studies of lighting for dense prediction and generation in computer vision"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:00Z"}