{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/86710"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/86710","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Human Mesh Reconstruction Through RF Signal","abstract":"M.S.","abstract_html":"M.S.","abstract_has_math":false,"creators":["Shi, Bilin; 0000-0001-9449-9348"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Su, Lu","Computer Science and Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02-21T21:36:43Z","date_published":"2025-02-21T21:36:43Z","updated_at":"2026-07-27T19:05:34Z","subjects":["artificial intelligence"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/86710","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Su, Lu","Computer Science and Engineering"]},{"key":"dc:creator","label":"Author","values":["Shi, Bilin; 0000-0001-9449-9348"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-02-21T21:36:43Z","2020"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["artificial intelligence"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/86710"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["M.S.","Recently the human reconstruction in real world has become a spotlight task in Internet of Things (IOT) field and significant efforts have been made to explore device-free human skeleton reconstruction techniques that utilize the information from RF-signal. However the human mesh reconstruction task through commercial WiFi devices is still lack of explo- ration, which would be a more general solution to capture the human activities and expand the applicable scenarios of IOT. So in this paper we propose a deep learning framework to reconstruct 3D human Mesh from RF signals collected by commercial WiFi devices. From the pervasive WiFi signals, our framework can extract both shape and pose parameters of human body and construct the Skinned Multi-Person Linear (SMPL) human mesh. Besides, we also build a multi-camera 3D human skeleton reconstruction system which can output accurate human skeleton in complex scenes. This skeleton system makes it available to train our framework in more complex scenarios, which greatly improves the capacity of our framework. The evaluation results over multiple different motions collected from a real-world WiFi sensing testbed shows that our framework can reconstruct the 3D human mesh within centimeter-level error, which indicates the strong reconstructive potentiality of the framework.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Human Mesh Reconstruction Through RF Signal"]}]}],"canonical_facts":{"dc:contributor":["Su, Lu","Computer Science and Engineering"],"dc:creator":["Shi, Bilin; 0000-0001-9449-9348"],"dc:date":["2025-02-21T21:36:43Z","2020"],"dc:description":["M.S.","Recently the human reconstruction in real world has become a spotlight task in Internet of Things (IOT) field and significant efforts have been made to explore device-free human skeleton reconstruction techniques that utilize the information from RF-signal. However the human mesh reconstruction task through commercial WiFi devices is still lack of explo- ration, which would be a more general solution to capture the human activities and expand the applicable scenarios of IOT. So in this paper we propose a deep learning framework to reconstruct 3D human Mesh from RF signals collected by commercial WiFi devices. From the pervasive WiFi signals, our framework can extract both shape and pose parameters of human body and construct the Skinned Multi-Person Linear (SMPL) human mesh. Besides, we also build a multi-camera 3D human skeleton reconstruction system which can output accurate human skeleton in complex scenes. This skeleton system makes it available to train our framework in more complex scenarios, which greatly improves the capacity of our framework. The evaluation results over multiple different motions collected from a real-world WiFi sensing testbed shows that our framework can reconstruct the 3D human mesh within centimeter-level error, which indicates the strong reconstructive potentiality of the framework.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/86710"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["artificial intelligence"],"dc:title":["Human Mesh Reconstruction Through RF Signal"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T19:05:34Z"}