{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/121554"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/121554","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Mapprior: Bird's-eye view perception with generative models","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-12-04 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-12-04 without embargo terms","abstract_has_math":false,"creators":["Zhu, Xiyue"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Wang, Shenlong","Kindratenko, Volodymyr"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-08","date_published":"2023-08","updated_at":"2026-07-22T22:25:00Z","subjects":["Bev Perception","Bev Map Segmentation","Generative Models","Vqgan","Autonomous Driving"],"languages":["en","eng"],"rights":["Copyright 2023 Xiyue Zhu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/121554","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Wang, Shenlong","Kindratenko, Volodymyr"]},{"key":"dc:creator","label":"Author","values":["Zhu, Xiyue"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-08","2023-07-21"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"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":["Bev Perception","Bev Map Segmentation","Generative Models","Vqgan","Autonomous Driving"]}]},{"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 Xiyue Zhu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/121554"]}]},{"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 2023-12-04 without embargo terms","The student, Xiyue Zhu, accepted the attached license on 2023-07-19 at 16:10.","The student, Xiyue Zhu, submitted this Thesis for approval on 2023-07-19 at 18:23.","This Thesis was approved for publication on 2023-07-21 at 07:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19744 on 2023-12-04 at 17:03:29","This thesis presents a novel generative methodology in bird’s-eye view map segmentation. Despite tremendous advancements in bird’s-eye view (BEV) perception, existing models fall short in generating realistic and coherent semantic map layouts, and they fail to account for uncertainties arising from partial sensor information (such as occlusion or limited coverage). This thesis introduces MapPrior, a novel BEV perception framework that combines a traditional discriminative BEV perception model with a learned generative model for semantic map layouts. Our MapPrior delivers predictions with better accuracy, realism, and uncertainty awareness. Evaluated on the large-scale nuScenes benchmark, it establishes a new state-of-the-art mean IoU score, with significantly improved MMD and ECE scores, for both cameras- and LiDAR-based BEV perception models. Furthermore, our method can be used to perpetually generate layouts with unconditional sampling."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Mapprior: Bird's-eye view perception with generative models"]}]}],"canonical_facts":{"dc:contributor":["Wang, Shenlong","Kindratenko, Volodymyr"],"dc:creator":["Zhu, Xiyue"],"dc:date":["2023-08","2023-07-21"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-12-04 without embargo terms","The student, Xiyue Zhu, accepted the attached license on 2023-07-19 at 16:10.","The student, Xiyue Zhu, submitted this Thesis for approval on 2023-07-19 at 18:23.","This Thesis was approved for publication on 2023-07-21 at 07:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19744 on 2023-12-04 at 17:03:29","This thesis presents a novel generative methodology in bird’s-eye view map segmentation. Despite tremendous advancements in bird’s-eye view (BEV) perception, existing models fall short in generating realistic and coherent semantic map layouts, and they fail to account for uncertainties arising from partial sensor information (such as occlusion or limited coverage). This thesis introduces MapPrior, a novel BEV perception framework that combines a traditional discriminative BEV perception model with a learned generative model for semantic map layouts. Our MapPrior delivers predictions with better accuracy, realism, and uncertainty awareness. Evaluated on the large-scale nuScenes benchmark, it establishes a new state-of-the-art mean IoU score, with significantly improved MMD and ECE scores, for both cameras- and LiDAR-based BEV perception models. Furthermore, our method can be used to perpetually generate layouts with unconditional sampling."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/121554"],"dc:language":["en","eng"],"dc:rights":["Copyright 2023 Xiyue Zhu"],"dc:subject":["Bev Perception","Bev Map Segmentation","Generative Models","Vqgan","Autonomous Driving"],"dc:title":["Mapprior: Bird's-eye view perception with generative models"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"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"}