{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/72806"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/72806","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Single view object completion","abstract":"The goal of this paper is to achieve complete reconstruction of a 3d object from a single depth image observation. Much effort has been put on multi-view reconstruction of objects with substantial success, but single view recon- struction is still very limited. Initial methods produce only partial reconstructions by projecting a depth map. State of the art approaches achieve complete reconstruction but either require user interaction or perform successfully on only a handful of simple categories. The method described in this paper is an exemplar based approach to fully au- tomated reconstruction of a large variety of object classes using only a single depth image. The approach has three major components: retrieving a similar object, fitting the matched object to the query point cloud using alignment and symmetries, and reconstructing the mesh using the exemplar as a template. This method is evaluated in three distinct experiments: novel category (query of untrained class), novel model (query of trained class, untrained model), and novel view (query of trained model from a new viewpoint).","abstract_html":"The goal of this paper is to achieve complete reconstruction of a 3d object from a single depth image observation. Much effort has been put on multi-view reconstruction of objects with substantial success, but single view recon- struction is still very limited. Initial methods produce only partial reconstructions by projecting a depth map. State of the art approaches achieve complete reconstruction but either require user interaction or perform successfully on only a handful of simple categories. The method described in this paper is an exemplar based approach to fully au- tomated reconstruction of a large variety of object classes using only a single depth image. The approach has three major components: retrieving a similar object, fitting the matched object to the query point cloud using alignment and symmetries, and reconstructing the mesh using the exemplar as a template. This method is evaluated in three distinct experiments: novel category (query of untrained class), novel model (query of trained class, untrained model), and novel view (query of trained model from a new viewpoint).","abstract_has_math":false,"creators":["Thorsen, Justin"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Hoiem, Derek W."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-01-21T19:48:24Z","date_published":"2015-01-21T19:48:24Z","updated_at":"2026-07-22T22:26:07Z","subjects":["Single view object reconstruction","Object completion from a depth map","Partial view matching","Object deformation"],"languages":["en"],"rights":["Copyright 2014 Justin Thorsen"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/72806","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hoiem, Derek W."]},{"key":"dc:creator","label":"Author","values":["Thorsen, Justin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-01-21T19:48:24Z","2014-12","2015-01-21"]},{"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":["Single view object reconstruction","Object completion from a depth map","Partial view matching","Object deformation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2014 Justin Thorsen"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/72806"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The goal of this paper is to achieve complete reconstruction of a 3d object from a single depth image observation. Much effort has been put on multi-view reconstruction of objects with substantial success, but single view recon- struction is still very limited. Initial methods produce only partial reconstructions by projecting a depth map. State of the art approaches achieve complete reconstruction but either require user interaction or perform successfully on only a handful of simple categories. The method described in this paper is an exemplar based approach to fully au- tomated reconstruction of a large variety of object classes using only a single depth image. The approach has three major components: retrieving a similar object, fitting the matched object to the query point cloud using alignment and symmetries, and reconstructing the mesh using the exemplar as a template. This method is evaluated in three distinct experiments: novel category (query of untrained class), novel model (query of trained class, untrained model), and novel view (query of trained model from a new viewpoint).","Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2014-12-08T13:56:26Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 thesis.tex: 52533 bytes, checksum: 0e4958b1b8ff89a68cc8eaadc0dc82b7 (MD5) Thorsen_Justin.pdf: 3489753 bytes, checksum: a333bbff6c69fc2c95db1df706a2330d (MD5)","Made available in DSpace on 2015-01-21T19:48:24Z (GMT). No. of bitstreams: 2 Justin_Thorsen.pdf: 3489730 bytes, checksum: 5a7ea5b740d448619cf0be3f6882c5a2 (MD5) thesis.tex: 52550 bytes, checksum: 5dd0eb8114da367879298729dfd454ee (MD5)"]},{"key":"dc:title","label":"Title","values":["Single view object completion"]}]}],"canonical_facts":{"dc:contributor":["Hoiem, Derek W."],"dc:creator":["Thorsen, Justin"],"dc:date":["2015-01-21T19:48:24Z","2014-12","2015-01-21"],"dc:description":["The goal of this paper is to achieve complete reconstruction of a 3d object from a single depth image observation. Much effort has been put on multi-view reconstruction of objects with substantial success, but single view recon- struction is still very limited. Initial methods produce only partial reconstructions by projecting a depth map. State of the art approaches achieve complete reconstruction but either require user interaction or perform successfully on only a handful of simple categories. The method described in this paper is an exemplar based approach to fully au- tomated reconstruction of a large variety of object classes using only a single depth image. The approach has three major components: retrieving a similar object, fitting the matched object to the query point cloud using alignment and symmetries, and reconstructing the mesh using the exemplar as a template. This method is evaluated in three distinct experiments: novel category (query of untrained class), novel model (query of trained class, untrained model), and novel view (query of trained model from a new viewpoint).","Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2014-12-08T13:56:26Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 thesis.tex: 52533 bytes, checksum: 0e4958b1b8ff89a68cc8eaadc0dc82b7 (MD5) Thorsen_Justin.pdf: 3489753 bytes, checksum: a333bbff6c69fc2c95db1df706a2330d (MD5)","Made available in DSpace on 2015-01-21T19:48:24Z (GMT). No. of bitstreams: 2 Justin_Thorsen.pdf: 3489730 bytes, checksum: 5a7ea5b740d448619cf0be3f6882c5a2 (MD5) thesis.tex: 52550 bytes, checksum: 5dd0eb8114da367879298729dfd454ee (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/72806"],"dc:language":["en"],"dc:rights":["Copyright 2014 Justin Thorsen"],"dc:subject":["Single view object reconstruction","Object completion from a depth map","Partial view matching","Object deformation"],"dc:title":["Single view object completion"],"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":"2026-07-22T22:26:07Z"}