{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/95307"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/95307","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Physically based geometry and reflectance recovery from images","abstract":"An image is a projection of the three-dimensional world taken at an instance in space and time. Its formation involves a complex interplay between geometry, illumination and material properties of objects in the scene. Given image data and knowledge of some scene properties, the recovery of the remaining components can be cast as a set of physically based inverse problems. This thesis investigates three inverse problems on the recovery of scene properties and discusses how we can develop appropriate physical constraints and build them into effective algorithms. Firstly, we study the problem of geometry recovery from a single image with repeated texture. Our technique leverages the PatchMatch algorithm to detect and match repeated patterns undergoing geometric transformations. This allows effective enforcement of translational symmetry constraint in the recovery of texture lattice. Secondly, we study the problem of computational relighting using RGB-D data, where the depth data is acquired through a Kinect sensor and is often noisy. We show how the inclusion of noisy depth input helps to resolve ambiguities in the recovery of shape and reflectance in the inverse rendering problem. Our results show that the complementary nature of RGB and depth is highly beneficial for a practical relighting system. Lastly, in the third problem, we exploit the use of geometric constraints relating two views, to address a challenging problem in Internet image matching. Our solution is robust to geometric and photometric distortions over wide baselines. It also accommodates repeated structures that are commonly found in our modern environment. Building on the image correspondence, we also investigate the use of color transfer as an additional global constraint in relating Internet images. It shows promising results in obtaining more accurate and denser correspondence.","abstract_html":"An image is a projection of the three-dimensional world taken at an instance in space and time. Its formation involves a complex interplay between geometry, illumination and material properties of objects in the scene. Given image data and knowledge of some scene properties, the recovery of the remaining components can be cast as a set of physically based inverse problems. This thesis investigates three inverse problems on the recovery of scene properties and discusses how we can develop appropriate physical constraints and build them into effective algorithms. Firstly, we study the problem of geometry recovery from a single image with repeated texture. Our technique leverages the PatchMatch algorithm to detect and match repeated patterns undergoing geometric transformations. This allows effective enforcement of translational symmetry constraint in the recovery of texture lattice. Secondly, we study the problem of computational relighting using RGB-D data, where the depth data is acquired through a Kinect sensor and is often noisy. We show how the inclusion of noisy depth input helps to resolve ambiguities in the recovery of shape and reflectance in the inverse rendering problem. Our results show that the complementary nature of RGB and depth is highly beneficial for a practical relighting system. Lastly, in the third problem, we exploit the use of geometric constraints relating two views, to address a challenging problem in Internet image matching. Our solution is robust to geometric and photometric distortions over wide baselines. It also accommodates repeated structures that are commonly found in our modern environment. Building on the image correspondence, we also investigate the use of color transfer as an additional global constraint in relating Internet images. It shows promising results in obtaining more accurate and denser correspondence.","abstract_has_math":false,"creators":["Liu, Siying"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Do, Minh N.","Kamalabadi, Farzad","Hasegawa-Johnson, Mark A.","Hart, John C."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017-03-01T15:46:19Z","date_published":"2017-03-01T15:46:19Z","updated_at":"2026-07-22T22:26:37Z","subjects":["texture","RGB-D","reflectance","image correspondence","color transfer"],"languages":["en"],"rights":["Copyright 2016 Siying Liu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/95307","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Do, Minh N.","Kamalabadi, Farzad","Hasegawa-Johnson, Mark A.","Hart, John C."]},{"key":"dc:creator","label":"Author","values":["Liu, Siying"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2017-03-01T15:46:19Z","2016-11-04","2016-12"]},{"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":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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":["texture","RGB-D","reflectance","image correspondence","color transfer"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2016 Siying Liu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/95307"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["An image is a projection of the three-dimensional world taken at an instance in space and time. Its formation involves a complex interplay between geometry, illumination and material properties of objects in the scene. Given image data and knowledge of some scene properties, the recovery of the remaining components can be cast as a set of physically based inverse problems. This thesis investigates three inverse problems on the recovery of scene properties and discusses how we can develop appropriate physical constraints and build them into effective algorithms. Firstly, we study the problem of geometry recovery from a single image with repeated texture. Our technique leverages the PatchMatch algorithm to detect and match repeated patterns undergoing geometric transformations. This allows effective enforcement of translational symmetry constraint in the recovery of texture lattice. Secondly, we study the problem of computational relighting using RGB-D data, where the depth data is acquired through a Kinect sensor and is often noisy. We show how the inclusion of noisy depth input helps to resolve ambiguities in the recovery of shape and reflectance in the inverse rendering problem. Our results show that the complementary nature of RGB and depth is highly beneficial for a practical relighting system. Lastly, in the third problem, we exploit the use of geometric constraints relating two views, to address a challenging problem in Internet image matching. Our solution is robust to geometric and photometric distortions over wide baselines. It also accommodates repeated structures that are commonly found in our modern environment. Building on the image correspondence, we also investigate the use of color transfer as an additional global constraint in relating Internet images. It shows promising results in obtaining more accurate and denser correspondence.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2017-02-28 without embargo terms","The student, Siying Liu, accepted the attached license on 2016-11-03 at 21:10.","The student, Siying Liu, submitted this Dissertation for approval on 2016-11-03 at 22:25.","This Dissertation was approved for publication on 2016-11-04 at 13:02.","DSpace SAF Submission Ingestion Package generated from Vireo submission #10219 on 2017-02-28 at 14:46:46","Made available in DSpace on 2017-03-01T15:46:19Z (GMT). No. of bitstreams: 3 LIU-DISSERTATION-2016.pdf: 20771295 bytes, checksum: b1b1f67b2f6ad55e7e2ce2e59e17d8f9 (MD5) LICENSE.txt: 4207 bytes, checksum: 5484f6f76315950880c57d488feefde8 (MD5) PROQUEST_LICENSE.txt: 4553 bytes, checksum: 679d4ef3adfa9e87cb21e67ddc383b77 (MD5) Previous issue date: 2016-11-04"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Physically based geometry and reflectance recovery from images"]}]}],"canonical_facts":{"dc:contributor":["Do, Minh N.","Kamalabadi, Farzad","Hasegawa-Johnson, Mark A.","Hart, John C."],"dc:creator":["Liu, Siying"],"dc:date":["2017-03-01T15:46:19Z","2016-11-04","2016-12"],"dc:description":["An image is a projection of the three-dimensional world taken at an instance in space and time. Its formation involves a complex interplay between geometry, illumination and material properties of objects in the scene. Given image data and knowledge of some scene properties, the recovery of the remaining components can be cast as a set of physically based inverse problems. This thesis investigates three inverse problems on the recovery of scene properties and discusses how we can develop appropriate physical constraints and build them into effective algorithms. Firstly, we study the problem of geometry recovery from a single image with repeated texture. Our technique leverages the PatchMatch algorithm to detect and match repeated patterns undergoing geometric transformations. This allows effective enforcement of translational symmetry constraint in the recovery of texture lattice. Secondly, we study the problem of computational relighting using RGB-D data, where the depth data is acquired through a Kinect sensor and is often noisy. We show how the inclusion of noisy depth input helps to resolve ambiguities in the recovery of shape and reflectance in the inverse rendering problem. Our results show that the complementary nature of RGB and depth is highly beneficial for a practical relighting system. Lastly, in the third problem, we exploit the use of geometric constraints relating two views, to address a challenging problem in Internet image matching. Our solution is robust to geometric and photometric distortions over wide baselines. It also accommodates repeated structures that are commonly found in our modern environment. Building on the image correspondence, we also investigate the use of color transfer as an additional global constraint in relating Internet images. It shows promising results in obtaining more accurate and denser correspondence.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2017-02-28 without embargo terms","The student, Siying Liu, accepted the attached license on 2016-11-03 at 21:10.","The student, Siying Liu, submitted this Dissertation for approval on 2016-11-03 at 22:25.","This Dissertation was approved for publication on 2016-11-04 at 13:02.","DSpace SAF Submission Ingestion Package generated from Vireo submission #10219 on 2017-02-28 at 14:46:46","Made available in DSpace on 2017-03-01T15:46:19Z (GMT). No. of bitstreams: 3 LIU-DISSERTATION-2016.pdf: 20771295 bytes, checksum: b1b1f67b2f6ad55e7e2ce2e59e17d8f9 (MD5) LICENSE.txt: 4207 bytes, checksum: 5484f6f76315950880c57d488feefde8 (MD5) PROQUEST_LICENSE.txt: 4553 bytes, checksum: 679d4ef3adfa9e87cb21e67ddc383b77 (MD5) Previous issue date: 2016-11-04"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/95307"],"dc:language":["en"],"dc:rights":["Copyright 2016 Siying Liu"],"dc:subject":["texture","RGB-D","reflectance","image correspondence","color transfer"],"dc:title":["Physically based geometry and reflectance recovery from images"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:37Z"}