{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/105848"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/105848","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Monocular depth prediction with object removal from single image","abstract":"Made available in DSpace on 2019-11-26T20:56:42Z (GMT). No. of bitstreams: 2 ISSARANON-THESIS-2019.pdf: 7688701 bytes, checksum: baa450593876648cfe266eb94e08f620 (MD5) LICENSE.txt: 4216 bytes, checksum: 2d6304943912f430c696ec1b407c7055 (MD5) Previous issue date: 2019-07-12","abstract_html":"Made available in DSpace on 2019-11-26T20:56:42Z (GMT). No. of bitstreams: 2 ISSARANON-THESIS-2019.pdf: 7688701 bytes, checksum: baa450593876648cfe266eb94e08f620 (MD5) LICENSE.txt: 4216 bytes, checksum: 2d6304943912f430c696ec1b407c7055 (MD5) Previous issue date: 2019-07-12","abstract_has_math":false,"creators":["Issaranon, Theerasit"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Forsyth, David"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-11-26T20:56:42Z","date_published":"2019-11-26T20:56:42Z","updated_at":"2026-07-22T22:24:45Z","subjects":["Single-Image Depth Prediction","Object Removal","Occluded Vision"],"languages":["en"],"rights":["Copyright 2019 Theerasit Issaranon"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/105848","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Forsyth, David"]},{"key":"dc:creator","label":"Author","values":["Issaranon, Theerasit"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-11-26T20:56:42Z","2021-11-27T10:15:37Z","2019-07-12","2019-08"]},{"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":["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-Image Depth Prediction","Object Removal","Occluded Vision"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2019 Theerasit Issaranon"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/105848"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Made available in DSpace on 2019-11-26T20:56:42Z (GMT). No. of bitstreams: 2 ISSARANON-THESIS-2019.pdf: 7688701 bytes, checksum: baa450593876648cfe266eb94e08f620 (MD5) LICENSE.txt: 4216 bytes, checksum: 2d6304943912f430c696ec1b407c7055 (MD5) Previous issue date: 2019-07-12","Embargo set by: Seth Robbins for item 112993 Lift date: 2021-11-26T20:56:50Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 112993 Lift date: 2021-11-26T20:58:03Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","We describe a method that predicts, from a single RGB image, a depth map that describes the scene when a masked object is removed – we call this “counterfactual depth” that models hidden scene geometry together with the observations. Our method works for the same reason that scene completion works: the spatial structure of objects is simple. But we offer a much higher resolution representation of space than current scene completion methods, as we operate at pixel-level precision and do not rely on a voxel representation. We can remove objects arbitrarily with an instructed object mask. Furthermore, we do not require RGBD inputs. Our method uses a standard encoder-decoder architecture, with a decoder modified to accept an object mask. We systematically construct a small evaluation dataset that we have collected. Using this dataset, we show that our depth predictions for masked objects are better than other baselines in the real scene. Given unmasked images, our approach performs comparatively well as a regular scene depth predictor.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2021-08-01","The student, Theerasit Issaranon, accepted the attached license on 2019-07-09 at 17:46.","The student, Theerasit Issaranon, submitted this Thesis for approval on 2019-07-09 at 18:06.","This Thesis was approved for publication on 2019-07-12 at 15:18.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13012 on 2019-11-26 at 13:59:14","Embargo set by: Seth Robbins for item 112993 Lift date: 2021-11-26T20:58:44Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 112993 Lift date: 2021-11-26T20:59:54Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 112993 on 2021-11-27T10:15:37Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Monocular depth prediction with object removal from single image"]}]}],"canonical_facts":{"dc:contributor":["Forsyth, David"],"dc:creator":["Issaranon, Theerasit"],"dc:date":["2019-11-26T20:56:42Z","2021-11-27T10:15:37Z","2019-07-12","2019-08"],"dc:description":["Made available in DSpace on 2019-11-26T20:56:42Z (GMT). No. of bitstreams: 2 ISSARANON-THESIS-2019.pdf: 7688701 bytes, checksum: baa450593876648cfe266eb94e08f620 (MD5) LICENSE.txt: 4216 bytes, checksum: 2d6304943912f430c696ec1b407c7055 (MD5) Previous issue date: 2019-07-12","Embargo set by: Seth Robbins for item 112993 Lift date: 2021-11-26T20:56:50Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 112993 Lift date: 2021-11-26T20:58:03Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","We describe a method that predicts, from a single RGB image, a depth map that describes the scene when a masked object is removed – we call this “counterfactual depth” that models hidden scene geometry together with the observations. Our method works for the same reason that scene completion works: the spatial structure of objects is simple. But we offer a much higher resolution representation of space than current scene completion methods, as we operate at pixel-level precision and do not rely on a voxel representation. We can remove objects arbitrarily with an instructed object mask. Furthermore, we do not require RGBD inputs. Our method uses a standard encoder-decoder architecture, with a decoder modified to accept an object mask. We systematically construct a small evaluation dataset that we have collected. Using this dataset, we show that our depth predictions for masked objects are better than other baselines in the real scene. Given unmasked images, our approach performs comparatively well as a regular scene depth predictor.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2021-08-01","The student, Theerasit Issaranon, accepted the attached license on 2019-07-09 at 17:46.","The student, Theerasit Issaranon, submitted this Thesis for approval on 2019-07-09 at 18:06.","This Thesis was approved for publication on 2019-07-12 at 15:18.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13012 on 2019-11-26 at 13:59:14","Embargo set by: Seth Robbins for item 112993 Lift date: 2021-11-26T20:58:44Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 112993 Lift date: 2021-11-26T20:59:54Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 112993 on 2021-11-27T10:15:37Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/105848"],"dc:language":["en"],"dc:rights":["Copyright 2019 Theerasit Issaranon"],"dc:subject":["Single-Image Depth Prediction","Object Removal","Occluded Vision"],"dc:title":["Monocular depth prediction with object removal from single image"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:45Z"}