{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/90821"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/90821","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Improve OpenMVG and create a novel algorithm for novel view synthesis from point clouds","abstract":"This thesis presents work to improve open source 3D reconstruction software OpenMVG and to create a novel algorithm to render photorealistic images from new views given a photo collection and 3D point cloud. First, the original OpenMVG is parallelized using GPU and its data structure is optimized. Moreover, we integrated the MatchMiner algorithm into OpenMVG to further improve its efficiency. Last but not least, an initial pair selection formulation and a default focal length setting are introduced and implemented to automize OpenMVG. Then 3D sparse point clouds of construction sites are reconstructed by performing Structure-from-Motion (SfM) with the improved version of OpenMVG and source images (images that are used in SfM) are calibrated and registered to point clouds. Furukawa's Patch-based Multi-view Stereo(PMVS) algorithm is used to reconstruct dense point clouds using calibrated cameras as inputs. With known depth values of 3D points in the dense point cloud, we estimate depth maps of source images using optimization similar to Levin's colorization algorithm. For a novel view of the point cloud, we find source images that share some common elements of the construction site that are also visible to the novel view. Then we warp depth maps of these candidate images to the novel view. We estimate a depth map and label pixels for the novel view by solving a multi-label Markov Random Field (MRF) optimization problem using graph-cuts. We introduce a novel energy minimization formulation exploits both 2D and 3D information. Finally, a photorealistic image of the novel view is rendered by copying pixel colors from selected candidate source images using pixel labels computed with graph-cuts. We experimentally validate our approach on several challenging viewing angles of a point cloud model of a complicate construction site. The rendered results show high photo-realistic synthesis quality in planar scenes.","abstract_html":"This thesis presents work to improve open source 3D reconstruction software OpenMVG and to create a novel algorithm to render photorealistic images from new views given a photo collection and 3D point cloud. First, the original OpenMVG is parallelized using GPU and its data structure is optimized. Moreover, we integrated the MatchMiner algorithm into OpenMVG to further improve its efficiency. Last but not least, an initial pair selection formulation and a default focal length setting are introduced and implemented to automize OpenMVG. Then 3D sparse point clouds of construction sites are reconstructed by performing Structure-from-Motion (SfM) with the improved version of OpenMVG and source images (images that are used in SfM) are calibrated and registered to point clouds. Furukawa's Patch-based Multi-view Stereo(PMVS) algorithm is used to reconstruct dense point clouds using calibrated cameras as inputs. With known depth values of 3D points in the dense point cloud, we estimate depth maps of source images using optimization similar to Levin's colorization algorithm. For a novel view of the point cloud, we find source images that share some common elements of the construction site that are also visible to the novel view. Then we warp depth maps of these candidate images to the novel view. We estimate a depth map and label pixels for the novel view by solving a multi-label Markov Random Field (MRF) optimization problem using graph-cuts. We introduce a novel energy minimization formulation exploits both 2D and 3D information. Finally, a photorealistic image of the novel view is rendered by copying pixel colors from selected candidate source images using pixel labels computed with graph-cuts. We experimentally validate our approach on several challenging viewing angles of a point cloud model of a complicate construction site. The rendered results show high photo-realistic synthesis quality in planar scenes.","abstract_has_math":false,"creators":["Tsoi, Ka Wai"],"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":2016,"date_issued":"2016-07-07T20:27:59Z","date_published":"2016-07-07T20:27:59Z","updated_at":"2026-07-22T22:26:34Z","subjects":["Computer Vision","Computer Science","Structure-from-Movtion","Novel View Synthesis"],"languages":["en"],"rights":["2016 Ka Wai Tsoi."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/90821","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":["Tsoi, Ka Wai"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2016-07-07T20:27:59Z","2018-07-08T09:15:27Z","2016-04-26","2016-05"]},{"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":["Computer Vision","Computer Science","Structure-from-Movtion","Novel View Synthesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["2016 Ka Wai Tsoi."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/90821"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This thesis presents work to improve open source 3D reconstruction software OpenMVG and to create a novel algorithm to render photorealistic images from new views given a photo collection and 3D point cloud. First, the original OpenMVG is parallelized using GPU and its data structure is optimized. Moreover, we integrated the MatchMiner algorithm into OpenMVG to further improve its efficiency. Last but not least, an initial pair selection formulation and a default focal length setting are introduced and implemented to automize OpenMVG. Then 3D sparse point clouds of construction sites are reconstructed by performing Structure-from-Motion (SfM) with the improved version of OpenMVG and source images (images that are used in SfM) are calibrated and registered to point clouds. Furukawa's Patch-based Multi-view Stereo(PMVS) algorithm is used to reconstruct dense point clouds using calibrated cameras as inputs. With known depth values of 3D points in the dense point cloud, we estimate depth maps of source images using optimization similar to Levin's colorization algorithm. For a novel view of the point cloud, we find source images that share some common elements of the construction site that are also visible to the novel view. Then we warp depth maps of these candidate images to the novel view. We estimate a depth map and label pixels for the novel view by solving a multi-label Markov Random Field (MRF) optimization problem using graph-cuts. We introduce a novel energy minimization formulation exploits both 2D and 3D information. Finally, a photorealistic image of the novel view is rendered by copying pixel colors from selected candidate source images using pixel labels computed with graph-cuts. We experimentally validate our approach on several challenging viewing angles of a point cloud model of a complicate construction site. The rendered results show high photo-realistic synthesis quality in planar scenes.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2018-05-01","The student, Ka Wai Tsoi, accepted the attached license on 2016-04-25 at 12:01.","The student, Ka Wai Tsoi, submitted this Thesis for approval on 2016-04-25 at 12:17.","This Thesis was approved for publication on 2016-04-26 at 08:40.","DSpace SAF Submission Ingestion Package generated from Vireo submission #9469 on 2016-07-07 at 13:50:42","Made available in DSpace on 2016-07-07T20:27:59Z (GMT). No. of bitstreams: 3 TSOI-THESIS-2016.pdf: 4497821 bytes, checksum: e74468a722e1fcab161e01b39627f2ad (MD5) MS_Thesis_UIUC_2016.zip: 12066355 bytes, checksum: 660301d28011e877c741d632bdc59b1c (MD5) LICENSE.txt: 4208 bytes, checksum: 66a9660e50c8c686139fbeadd914d861 (MD5) Previous issue date: 2016-04-26","Embargo set by: Seth Robbins for item 93173 Lift date: 2018-07-07T20:28:14Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 93173 Lift date: 2018-07-07T20:35:34Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 93173 on 2018-07-08T09:15:27Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Improve OpenMVG and create a novel algorithm for novel view synthesis from point clouds"]}]}],"canonical_facts":{"dc:contributor":["Hoiem, Derek W."],"dc:creator":["Tsoi, Ka Wai"],"dc:date":["2016-07-07T20:27:59Z","2018-07-08T09:15:27Z","2016-04-26","2016-05"],"dc:description":["This thesis presents work to improve open source 3D reconstruction software OpenMVG and to create a novel algorithm to render photorealistic images from new views given a photo collection and 3D point cloud. First, the original OpenMVG is parallelized using GPU and its data structure is optimized. Moreover, we integrated the MatchMiner algorithm into OpenMVG to further improve its efficiency. Last but not least, an initial pair selection formulation and a default focal length setting are introduced and implemented to automize OpenMVG. Then 3D sparse point clouds of construction sites are reconstructed by performing Structure-from-Motion (SfM) with the improved version of OpenMVG and source images (images that are used in SfM) are calibrated and registered to point clouds. Furukawa's Patch-based Multi-view Stereo(PMVS) algorithm is used to reconstruct dense point clouds using calibrated cameras as inputs. With known depth values of 3D points in the dense point cloud, we estimate depth maps of source images using optimization similar to Levin's colorization algorithm. For a novel view of the point cloud, we find source images that share some common elements of the construction site that are also visible to the novel view. Then we warp depth maps of these candidate images to the novel view. We estimate a depth map and label pixels for the novel view by solving a multi-label Markov Random Field (MRF) optimization problem using graph-cuts. We introduce a novel energy minimization formulation exploits both 2D and 3D information. Finally, a photorealistic image of the novel view is rendered by copying pixel colors from selected candidate source images using pixel labels computed with graph-cuts. We experimentally validate our approach on several challenging viewing angles of a point cloud model of a complicate construction site. The rendered results show high photo-realistic synthesis quality in planar scenes.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2018-05-01","The student, Ka Wai Tsoi, accepted the attached license on 2016-04-25 at 12:01.","The student, Ka Wai Tsoi, submitted this Thesis for approval on 2016-04-25 at 12:17.","This Thesis was approved for publication on 2016-04-26 at 08:40.","DSpace SAF Submission Ingestion Package generated from Vireo submission #9469 on 2016-07-07 at 13:50:42","Made available in DSpace on 2016-07-07T20:27:59Z (GMT). No. of bitstreams: 3 TSOI-THESIS-2016.pdf: 4497821 bytes, checksum: e74468a722e1fcab161e01b39627f2ad (MD5) MS_Thesis_UIUC_2016.zip: 12066355 bytes, checksum: 660301d28011e877c741d632bdc59b1c (MD5) LICENSE.txt: 4208 bytes, checksum: 66a9660e50c8c686139fbeadd914d861 (MD5) Previous issue date: 2016-04-26","Embargo set by: Seth Robbins for item 93173 Lift date: 2018-07-07T20:28:14Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 93173 Lift date: 2018-07-07T20:35:34Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 93173 on 2018-07-08T09:15:27Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/90821"],"dc:language":["en"],"dc:rights":["2016 Ka Wai Tsoi."],"dc:subject":["Computer Vision","Computer Science","Structure-from-Movtion","Novel View Synthesis"],"dc:title":["Improve OpenMVG and create a novel algorithm for novel view synthesis from point clouds"],"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":"2026-07-22T22:26:34Z"}