{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/1634"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/1634","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"Error estimation for single-image human body mesh reconstruction","abstract":"Human pose and shape estimation methods continue to suffer in situations where one or more parts of the body are occluded. More importantly, these methods cannot express when their predicted pose is incorrect. This has serious consequences when these methods are used in human-robot interaction scenarios, where we need methods that can evaluate their predictions and flag situations where they might be wrong. This work studies this problem. We propose a method that combines information from OpenPose and SPIN—two popular human pose and shape estimation methods—to highlight regions on the predicted mesh that are least reliable. We have evaluated the proposed approach on 3DPW, 3DOH, and Human3.6M datasets, and the results demonstrate our model’s effectiveness in identifying inaccurate regions of the human body mesh.","abstract_html":"Human pose and shape estimation methods continue to suffer in situations where one or more parts of the body are occluded. More importantly, these methods cannot express when their predicted pose is incorrect. This has serious consequences when these methods are used in human-robot interaction scenarios, where we need methods that can evaluate their predictions and flag situations where they might be wrong. This work studies this problem. We propose a method that combines information from OpenPose and SPIN—two popular human pose and shape estimation methods—to highlight regions on the predicted mesh that are least reliable. We have evaluated the proposed approach on 3DPW, 3DOH, and Human3.6M datasets, and the results demonstrate our model’s effectiveness in identifying inaccurate regions of the human body mesh.","abstract_has_math":false,"creators":["Jafarian, Hamoon"],"institution":"University of Ontario Institute of Technology","degree_name":"Master of Science (MSc)","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Qureshi, Faisal"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-05-01","date_published":"2023-05-01","updated_at":"2026-07-24T05:35:38Z","subjects":["Human mesh recovery","Human pose and shape estimation","OpenPose","SPIN","Error estimation"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/1634","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Qureshi, Faisal"]},{"key":"dc:creator","label":"Author","values":["Jafarian, Hamoon"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-06-13T18:21:50Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-06-13T18:21:50Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-05-01"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MSc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Human mesh recovery","Human pose and shape estimation","OpenPose","SPIN","Error estimation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10155/1634"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Human pose and shape estimation methods continue to suffer in situations where one or more parts of the body are occluded. More importantly, these methods cannot express when their predicted pose is incorrect. This has serious consequences when these methods are used in human-robot interaction scenarios, where we need methods that can evaluate their predictions and flag situations where they might be wrong. This work studies this problem. We propose a method that combines information from OpenPose and SPIN—two popular human pose and shape estimation methods—to highlight regions on the predicted mesh that are least reliable. We have evaluated the proposed approach on 3DPW, 3DOH, and Human3.6M datasets, and the results demonstrate our model’s effectiveness in identifying inaccurate regions of the human body mesh."]},{"key":"dc:title","label":"Title","values":["Error estimation for single-image human body mesh reconstruction"]}]}],"canonical_facts":{"dc:contributor.advisor":["Qureshi, Faisal"],"dc:creator":["Jafarian, Hamoon"],"dc:date.accessioned":["2023-06-13T18:21:50Z"],"dc:date.available":["2023-06-13T18:21:50Z"],"dc:date.issued":["2023-05-01"],"dc:description.abstract":["Human pose and shape estimation methods continue to suffer in situations where one or more parts of the body are occluded. More importantly, these methods cannot express when their predicted pose is incorrect. This has serious consequences when these methods are used in human-robot interaction scenarios, where we need methods that can evaluate their predictions and flag situations where they might be wrong. This work studies this problem. We propose a method that combines information from OpenPose and SPIN—two popular human pose and shape estimation methods—to highlight regions on the predicted mesh that are least reliable. We have evaluated the proposed approach on 3DPW, 3DOH, and Human3.6M datasets, and the results demonstrate our model’s effectiveness in identifying inaccurate regions of the human body mesh."],"dc:identifier.uri":["https://hdl.handle.net/10155/1634"],"dc:language.iso":["en"],"dc:subject":["Human mesh recovery","Human pose and shape estimation","OpenPose","SPIN","Error estimation"],"dc:title":["Error estimation for single-image human body mesh reconstruction"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science (MSc)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:38Z"}