{"id":{"repo_id":"uic","oai_identifier":"oai:figshare.com:article/32993858"},"canonical_url":"https://search.dev.ndltd.org/etd/uic/oai:figshare.com:article/32993858","repository":{"repo_id":"uic","name":"University of Illinois - Chicago","base_url":"https://api.figshare.com/v2/oai"},"display":{"title":"Generative AI for Human-Centric Design in Extended Reality Applications","abstract":"Extended Reality (XR) technologies are increasingly used as platforms for design, collaboration, and simulation, while recent advances in generative AI have enabled new forms of content creation within immersive environments. Despite this convergence, there remains a limited understanding of how generative systems can be designed and evaluated as human-centered tools that support human–AI co-creation in immersive environments. The dissertation is organized around three complementary research directions. First, empirical user studies investigate how different XR interactions affect user experience components, establishing a foundation for understanding human perception and action in immersive environments. Second, physiological and psychophysical experiments examine perceptual and cognitive responses in XR, providing insight into how immersion and sensory cues affect human experience beyond self-report. Finally, a generative framework using variational autoencoders and latent diffusion is proposed for generating anthropometrically plausible yet diverse 3D human body models, also referred to as avatars. Model evaluation combines quantitative measures of geometric accuracy and anthropometric validity with qualitative assessments of plausibility, followed by a user study that explores exploratory design behavior and human–AI co-creation in XR.","abstract_html":"Extended Reality (XR) technologies are increasingly used as platforms for design, collaboration, and simulation, while recent advances in generative AI have enabled new forms of content creation within immersive environments. Despite this convergence, there remains a limited understanding of how generative systems can be designed and evaluated as human-centered tools that support human–AI co-creation in immersive environments. The dissertation is organized around three complementary research directions. First, empirical user studies investigate how different XR interactions affect user experience components, establishing a foundation for understanding human perception and action in immersive environments. Second, physiological and psychophysical experiments examine perceptual and cognitive responses in XR, providing insight into how immersion and sensory cues affect human experience beyond self-report. Finally, a generative framework using variational autoencoders and latent diffusion is proposed for generating anthropometrically plausible yet diverse 3D human body models, also referred to as avatars. Model evaluation combines quantitative measures of geometric accuracy and anthropometric validity with qualitative assessments of plausibility, followed by a user study that explores exploratory design behavior and human–AI co-creation in XR.","abstract_has_math":false,"creators":["Yalda Ghasemi (24399422)"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-05-01T00:00:00Z","date_published":"2026-05-01T00:00:00Z","updated_at":"2026-07-27T21:33:39Z","subjects":["Human-Computer Interaction"],"languages":[],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.25417/uic.32993858.v1","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Yalda Ghasemi (24399422)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026-05-01T00:00:00Z"]},{"key":"dc:relation","label":"Dc Relation","values":["https://figshare.com/articles/thesis/Generative_AI_for_Human-Centric_Design_in_Extended_Reality_Applications/32993858"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Human-Computer Interaction"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.25417/uic.32993858.v1"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Extended Reality (XR) technologies are increasingly used as platforms for design, collaboration, and simulation, while recent advances in generative AI have enabled new forms of content creation within immersive environments. Despite this convergence, there remains a limited understanding of how generative systems can be designed and evaluated as human-centered tools that support human–AI co-creation in immersive environments. The dissertation is organized around three complementary research directions. First, empirical user studies investigate how different XR interactions affect user experience components, establishing a foundation for understanding human perception and action in immersive environments. Second, physiological and psychophysical experiments examine perceptual and cognitive responses in XR, providing insight into how immersion and sensory cues affect human experience beyond self-report. Finally, a generative framework using variational autoencoders and latent diffusion is proposed for generating anthropometrically plausible yet diverse 3D human body models, also referred to as avatars. Model evaluation combines quantitative measures of geometric accuracy and anthropometric validity with qualitative assessments of plausibility, followed by a user study that explores exploratory design behavior and human–AI co-creation in XR."]},{"key":"dc:title","label":"Title","values":["Generative AI for Human-Centric Design in Extended Reality Applications"]}]}],"canonical_facts":{"dc:creator":["Yalda Ghasemi (24399422)"],"dc:date":["2026-05-01T00:00:00Z"],"dc:description":["Extended Reality (XR) technologies are increasingly used as platforms for design, collaboration, and simulation, while recent advances in generative AI have enabled new forms of content creation within immersive environments. Despite this convergence, there remains a limited understanding of how generative systems can be designed and evaluated as human-centered tools that support human–AI co-creation in immersive environments. The dissertation is organized around three complementary research directions. First, empirical user studies investigate how different XR interactions affect user experience components, establishing a foundation for understanding human perception and action in immersive environments. Second, physiological and psychophysical experiments examine perceptual and cognitive responses in XR, providing insight into how immersion and sensory cues affect human experience beyond self-report. Finally, a generative framework using variational autoencoders and latent diffusion is proposed for generating anthropometrically plausible yet diverse 3D human body models, also referred to as avatars. Model evaluation combines quantitative measures of geometric accuracy and anthropometric validity with qualitative assessments of plausibility, followed by a user study that explores exploratory design behavior and human–AI co-creation in XR."],"dc:identifier":["10.25417/uic.32993858.v1"],"dc:relation":["https://figshare.com/articles/thesis/Generative_AI_for_Human-Centric_Design_in_Extended_Reality_Applications/32993858"],"dc:rights":["In Copyright"],"dc:subject":["Human-Computer Interaction"],"dc:title":["Generative AI for Human-Centric Design in Extended Reality Applications"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T21:33:39Z"}