{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/78327"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/78327","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Inverse rendering techniques for physically grounded image editing","abstract":"\"From a single picture of a scene, people can typically grasp the spatial layout immediately and even make good guesses at materials properties and where light is coming from to illuminate the scene. For example, we can reliably tell which objects occlude others, what an object is made of and its rough shape, regions that are illuminated or in shadow, and so on. It is interesting how little is known about our ability to make these determinations; as such, we are still not able to robustly \"\"teach\"\" computers to make the same high-level observations as people. This document presents algorithms for understanding intrinsic scene properties from single images. The goal of these inverse rendering techniques is to estimate the configurations of scene elements (geometry, materials, luminaires, camera parameters, etc) using only information visible in an image. Such algorithms have applications in robotics and computer graphics. One such application is in physically grounded image editing: photo editing made easier by leveraging knowledge of the physical space. These applications allow sophisticated editing operations to be performed in a matter of seconds, enabling seamless addition, removal, or relocation of objects in images.\"","abstract_html":""From a single picture of a scene, people can typically grasp the spatial layout immediately and even make good guesses at materials properties and where light is coming from to illuminate the scene. For example, we can reliably tell which objects occlude others, what an object is made of and its rough shape, regions that are illuminated or in shadow, and so on. It is interesting how little is known about our ability to make these determinations; as such, we are still not able to robustly ""teach"" computers to make the same high-level observations as people. This document presents algorithms for understanding intrinsic scene properties from single images. The goal of these inverse rendering techniques is to estimate the configurations of scene elements (geometry, materials, luminaires, camera parameters, etc) using only information visible in an image. Such algorithms have applications in robotics and computer graphics. One such application is in physically grounded image editing: photo editing made easier by leveraging knowledge of the physical space. These applications allow sophisticated editing operations to be performed in a matter of seconds, enabling seamless addition, removal, or relocation of objects in images."","abstract_has_math":false,"creators":["Karsch, Kevin"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Forsyth, David A.","Hoiem, Derek W.","Hart, John","Kang, Sing Bing"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-07-22T22:16:09Z","date_published":"2015-07-22T22:16:09Z","updated_at":"2026-07-22T22:26:11Z","subjects":["image editing","scene understanding","inverse rendering"],"languages":[],"rights":["Copyright 2015 Kevin Karsch"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/78327","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Forsyth, David A.","Hoiem, Derek W.","Hart, John","Kang, Sing Bing"]},{"key":"dc:creator","label":"Author","values":["Karsch, Kevin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-07-22T22:16:09Z","2015-05","2015-03-10","2015-5"]},{"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":["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":["image editing","scene understanding","inverse rendering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2015 Kevin Karsch"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/78327"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["\"From a single picture of a scene, people can typically grasp the spatial layout immediately and even make good guesses at materials properties and where light is coming from to illuminate the scene. For example, we can reliably tell which objects occlude others, what an object is made of and its rough shape, regions that are illuminated or in shadow, and so on. It is interesting how little is known about our ability to make these determinations; as such, we are still not able to robustly \"\"teach\"\" computers to make the same high-level observations as people. This document presents algorithms for understanding intrinsic scene properties from single images. The goal of these inverse rendering techniques is to estimate the configurations of scene elements (geometry, materials, luminaires, camera parameters, etc) using only information visible in an image. Such algorithms have applications in robotics and computer graphics. One such application is in physically grounded image editing: photo editing made easier by leveraging knowledge of the physical space. These applications allow sophisticated editing operations to be performed in a matter of seconds, enabling seamless addition, removal, or relocation of objects in images.\"","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2015-07-22 without embargo terms","The student, Kevin Karsch, accepted the attached license on 2015-03-07 at 16:49.","The student, Kevin Karsch, submitted this Dissertation for approval on 2015-03-07 at 17:14.","This Dissertation was approved for publication on 2015-03-10 at 11:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #7741 on 2015-07-22 at 10:30:27","Made available in DSpace on 2015-07-22T22:16:09Z (GMT). No. of bitstreams: 2 Karsch_Kevin1.pdf: 143612586 bytes, checksum: b76da1fd491c3933a0b9f501d1feff27 (MD5) license.txt: 4061 bytes, checksum: ce72b6caf683f95185d27733e8154026 (MD5) Previous issue date: 2015-03-10"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Inverse rendering techniques for physically grounded image editing"]}]}],"canonical_facts":{"dc:contributor":["Forsyth, David A.","Hoiem, Derek W.","Hart, John","Kang, Sing Bing"],"dc:creator":["Karsch, Kevin"],"dc:date":["2015-07-22T22:16:09Z","2015-05","2015-03-10","2015-5"],"dc:description":["\"From a single picture of a scene, people can typically grasp the spatial layout immediately and even make good guesses at materials properties and where light is coming from to illuminate the scene. For example, we can reliably tell which objects occlude others, what an object is made of and its rough shape, regions that are illuminated or in shadow, and so on. It is interesting how little is known about our ability to make these determinations; as such, we are still not able to robustly \"\"teach\"\" computers to make the same high-level observations as people. This document presents algorithms for understanding intrinsic scene properties from single images. The goal of these inverse rendering techniques is to estimate the configurations of scene elements (geometry, materials, luminaires, camera parameters, etc) using only information visible in an image. Such algorithms have applications in robotics and computer graphics. One such application is in physically grounded image editing: photo editing made easier by leveraging knowledge of the physical space. These applications allow sophisticated editing operations to be performed in a matter of seconds, enabling seamless addition, removal, or relocation of objects in images.\"","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2015-07-22 without embargo terms","The student, Kevin Karsch, accepted the attached license on 2015-03-07 at 16:49.","The student, Kevin Karsch, submitted this Dissertation for approval on 2015-03-07 at 17:14.","This Dissertation was approved for publication on 2015-03-10 at 11:54.","DSpace SAF Submission Ingestion Package generated from Vireo submission #7741 on 2015-07-22 at 10:30:27","Made available in DSpace on 2015-07-22T22:16:09Z (GMT). No. of bitstreams: 2 Karsch_Kevin1.pdf: 143612586 bytes, checksum: b76da1fd491c3933a0b9f501d1feff27 (MD5) license.txt: 4061 bytes, checksum: ce72b6caf683f95185d27733e8154026 (MD5) Previous issue date: 2015-03-10"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/78327"],"dc:rights":["Copyright 2015 Kevin Karsch"],"dc:subject":["image editing","scene understanding","inverse rendering"],"dc:title":["Inverse rendering techniques for physically grounded image editing"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:11Z"}