{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/26108"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/26108","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Kinect cloud normals: towards surface orientation estimation","abstract":"Since the early days of Computer Vision, we have explored what is possible in the realm of ‘Scene Understanding’. The advent of consumer-grade RGBD cameras has broadened the possibilities within this realm. The data they provide is able to serve as ground truth information or training data for a class of algorithms, which would otherwise be extremely difficult, if not impossible, to train. This thesis serves the purpose of gathering data from such a source, specifically, it demonstrates how to collect a dual pair of depth and RGB images of a multitude of scenes and an approach to determine surface normals from these images. The goal of this endeavor is to provide a dataset of RGB images and surface normal estimates for each image so that the latter may serve as the ground truth for both training and evaluation of algorithms estimating surface normals from the RGB image alone.","abstract_html":"Since the early days of Computer Vision, we have explored what is possible in the realm of ‘Scene Understanding’. The advent of consumer-grade RGBD cameras has broadened the possibilities within this realm. The data they provide is able to serve as ground truth information or training data for a class of algorithms, which would otherwise be extremely difficult, if not impossible, to train. This thesis serves the purpose of gathering data from such a source, specifically, it demonstrates how to collect a dual pair of depth and RGB images of a multitude of scenes and an approach to determine surface normals from these images. The goal of this endeavor is to provide a dataset of RGB images and surface normal estimates for each image so that the latter may serve as the ground truth for both training and evaluation of algorithms estimating surface normals from the RGB image alone.","abstract_has_math":false,"creators":["Rungta, Pratik S."],"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":2011,"date_issued":"2011-08-25T22:14:25Z","date_published":"2011-08-25T22:14:25Z","updated_at":"2026-07-22T22:25:26Z","subjects":["microsoft kinect","dataset","point cloud","normal estimation"],"languages":["en"],"rights":["Copyright 2011 Pratik S. Rungta"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/26108","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":["Rungta, Pratik S."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2011-08-25T22:14:25Z","2011-08"]},{"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":["microsoft kinect","dataset","point cloud","normal estimation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2011 Pratik S. Rungta"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/26108"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Since the early days of Computer Vision, we have explored what is possible in the realm of ‘Scene Understanding’. The advent of consumer-grade RGBD cameras has broadened the possibilities within this realm. The data they provide is able to serve as ground truth information or training data for a class of algorithms, which would otherwise be extremely difficult, if not impossible, to train. This thesis serves the purpose of gathering data from such a source, specifically, it demonstrates how to collect a dual pair of depth and RGB images of a multitude of scenes and an approach to determine surface normals from these images. The goal of this endeavor is to provide a dataset of RGB images and surface normal estimates for each image so that the latter may serve as the ground truth for both training and evaluation of algorithms estimating surface normals from the RGB image alone.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2011-07-20T14:35:01Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 6 matlab_tools.zip: 4900 bytes, checksum: b87a5c8b40a64515f2d01f1b556d60f8 (MD5) workspace_files_part3.zip: 75988862 bytes, checksum: be3f2c3b4d75d75c0f213aecd53821c3 (MD5) workspace_files_part2.zip: 464444784 bytes, checksum: 41761f2c7e908d0433760ceddfabb9b2 (MD5) workspace_files_part1.zip: 508208687 bytes, checksum: fe41e7d88497fdf1f2704d70aa972677 (MD5) raw_data.zip: 314295100 bytes, checksum: 43b7299eae21f9e7453dcecbb9e49a8c (MD5) Rungta_Pratik.pdf: 12495625 bytes, checksum: 62c96cef0d92b4bf55ae5f69e4a2b705 (MD5)","Made available in DSpace on 2011-08-25T22:14:25Z (GMT). No. of bitstreams: 7 raw_data.zip: 314295100 bytes, checksum: 43b7299eae21f9e7453dcecbb9e49a8c (MD5) workspace_files_part1.zip: 508208687 bytes, checksum: fe41e7d88497fdf1f2704d70aa972677 (MD5) workspace_files_part2.zip: 464444784 bytes, checksum: 41761f2c7e908d0433760ceddfabb9b2 (MD5) workspace_files_part3.zip: 75988862 bytes, checksum: be3f2c3b4d75d75c0f213aecd53821c3 (MD5) matlab_tools.zip: 4900 bytes, checksum: b87a5c8b40a64515f2d01f1b556d60f8 (MD5) Rungta_Pratik.pdf: 12495625 bytes, checksum: 62c96cef0d92b4bf55ae5f69e4a2b705 (MD5) license.txt: 4063 bytes, checksum: 96b4acd9146ae2d16558960a8852db82 (MD5)"]},{"key":"dc:title","label":"Title","values":["Kinect cloud normals: towards surface orientation estimation"]}]}],"canonical_facts":{"dc:contributor":["Hoiem, Derek W."],"dc:creator":["Rungta, Pratik S."],"dc:date":["2011-08-25T22:14:25Z","2011-08"],"dc:description":["Since the early days of Computer Vision, we have explored what is possible in the realm of ‘Scene Understanding’. The advent of consumer-grade RGBD cameras has broadened the possibilities within this realm. The data they provide is able to serve as ground truth information or training data for a class of algorithms, which would otherwise be extremely difficult, if not impossible, to train. This thesis serves the purpose of gathering data from such a source, specifically, it demonstrates how to collect a dual pair of depth and RGB images of a multitude of scenes and an approach to determine surface normals from these images. The goal of this endeavor is to provide a dataset of RGB images and surface normal estimates for each image so that the latter may serve as the ground truth for both training and evaluation of algorithms estimating surface normals from the RGB image alone.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2011-07-20T14:35:01Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 6 matlab_tools.zip: 4900 bytes, checksum: b87a5c8b40a64515f2d01f1b556d60f8 (MD5) workspace_files_part3.zip: 75988862 bytes, checksum: be3f2c3b4d75d75c0f213aecd53821c3 (MD5) workspace_files_part2.zip: 464444784 bytes, checksum: 41761f2c7e908d0433760ceddfabb9b2 (MD5) workspace_files_part1.zip: 508208687 bytes, checksum: fe41e7d88497fdf1f2704d70aa972677 (MD5) raw_data.zip: 314295100 bytes, checksum: 43b7299eae21f9e7453dcecbb9e49a8c (MD5) Rungta_Pratik.pdf: 12495625 bytes, checksum: 62c96cef0d92b4bf55ae5f69e4a2b705 (MD5)","Made available in DSpace on 2011-08-25T22:14:25Z (GMT). No. of bitstreams: 7 raw_data.zip: 314295100 bytes, checksum: 43b7299eae21f9e7453dcecbb9e49a8c (MD5) workspace_files_part1.zip: 508208687 bytes, checksum: fe41e7d88497fdf1f2704d70aa972677 (MD5) workspace_files_part2.zip: 464444784 bytes, checksum: 41761f2c7e908d0433760ceddfabb9b2 (MD5) workspace_files_part3.zip: 75988862 bytes, checksum: be3f2c3b4d75d75c0f213aecd53821c3 (MD5) matlab_tools.zip: 4900 bytes, checksum: b87a5c8b40a64515f2d01f1b556d60f8 (MD5) Rungta_Pratik.pdf: 12495625 bytes, checksum: 62c96cef0d92b4bf55ae5f69e4a2b705 (MD5) license.txt: 4063 bytes, checksum: 96b4acd9146ae2d16558960a8852db82 (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/26108"],"dc:language":["en"],"dc:rights":["Copyright 2011 Pratik S. Rungta"],"dc:subject":["microsoft kinect","dataset","point cloud","normal estimation"],"dc:title":["Kinect cloud normals: towards surface orientation estimation"],"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":"2026-07-22T22:25:26Z"}