{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/101770"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/101770","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"DeepMVS: learning multi-view stereopsis","abstract":"We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction. Taking an arbitrary number of posed images as input, we first produce a set of plane-sweep volumes and use the proposed DeepMVS network to predict high-quality disparity maps. The key contributions that enable these results are (1) supervised pretraining on a photorealistic synthetic dataset, (2) an effective method for aggregating information across a set of unordered images, and (3) integrating multi-layer feature activations from the pre-trained VGG-19 network. We validate the efficacy of DeepMVS using the ETH3D Benchmark. Our results show that DeepMVS compares favorably against state-of-the-art conventional MVS algorithms and other ConvNet based methods, particularly for near-textureless regions and thin structures.","abstract_html":"We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction. Taking an arbitrary number of posed images as input, we first produce a set of plane-sweep volumes and use the proposed DeepMVS network to predict high-quality disparity maps. The key contributions that enable these results are (1) supervised pretraining on a photorealistic synthetic dataset, (2) an effective method for aggregating information across a set of unordered images, and (3) integrating multi-layer feature activations from the pre-trained VGG-19 network. We validate the efficacy of DeepMVS using the ETH3D Benchmark. Our results show that DeepMVS compares favorably against state-of-the-art conventional MVS algorithms and other ConvNet based methods, particularly for near-textureless regions and thin structures.","abstract_has_math":false,"creators":["Huang, Po-Han"],"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":["Ahuja, Narendra"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-09-27T16:45:34Z","date_published":"2018-09-27T16:45:34Z","updated_at":"2026-07-22T22:24:40Z","subjects":["computer vision, deep learning, multi-view stereo, DeepMVS, pattern recognition, 3D reconstruction, depth estimation, machine learning, convolutional neural network"],"languages":["en"],"rights":["Copyright 2018 Po-Han Huang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/101770","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ahuja, Narendra"]},{"key":"dc:creator","label":"Author","values":["Huang, Po-Han"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-09-27T16:45:34Z","2020-09-28T09:15:22Z","2018-06-25","2018-08"]},{"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":["computer vision, deep learning, multi-view stereo, DeepMVS, pattern recognition, 3D reconstruction, depth estimation, machine learning, convolutional neural network"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2018 Po-Han Huang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/101770"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction. Taking an arbitrary number of posed images as input, we first produce a set of plane-sweep volumes and use the proposed DeepMVS network to predict high-quality disparity maps. The key contributions that enable these results are (1) supervised pretraining on a photorealistic synthetic dataset, (2) an effective method for aggregating information across a set of unordered images, and (3) integrating multi-layer feature activations from the pre-trained VGG-19 network. We validate the efficacy of DeepMVS using the ETH3D Benchmark. Our results show that DeepMVS compares favorably against state-of-the-art conventional MVS algorithms and other ConvNet based methods, particularly for near-textureless regions and thin structures.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2020-08-01","The student, Po-Han Huang, accepted the attached license on 2018-06-25 at 02:03.","The student, Po-Han Huang, submitted this Thesis for approval on 2018-06-25 at 02:08.","This Thesis was approved for publication on 2018-06-25 at 15:24.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12668 on 2018-09-27 at 11:33:39","Made available in DSpace on 2018-09-27T16:45:34Z (GMT). No. of bitstreams: 2 HUANG-THESIS-2018.pdf: 11339483 bytes, checksum: 538ad32f08093c8f042b591e6f822a7d (MD5) LICENSE.txt: 4209 bytes, checksum: 6d984b618e6c62815c7a78e89454431a (MD5) Previous issue date: 2018-06-25","Embargo set by: Seth Robbins for item 107870 Lift date: 2020-09-27T16:45:39Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107870 Lift date: 2020-09-27T16:47:41Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 107870 on 2020-09-28T09:15:22Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["DeepMVS: learning multi-view stereopsis"]}]}],"canonical_facts":{"dc:contributor":["Ahuja, Narendra"],"dc:creator":["Huang, Po-Han"],"dc:date":["2018-09-27T16:45:34Z","2020-09-28T09:15:22Z","2018-06-25","2018-08"],"dc:description":["We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction. Taking an arbitrary number of posed images as input, we first produce a set of plane-sweep volumes and use the proposed DeepMVS network to predict high-quality disparity maps. The key contributions that enable these results are (1) supervised pretraining on a photorealistic synthetic dataset, (2) an effective method for aggregating information across a set of unordered images, and (3) integrating multi-layer feature activations from the pre-trained VGG-19 network. We validate the efficacy of DeepMVS using the ETH3D Benchmark. Our results show that DeepMVS compares favorably against state-of-the-art conventional MVS algorithms and other ConvNet based methods, particularly for near-textureless regions and thin structures.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2020-08-01","The student, Po-Han Huang, accepted the attached license on 2018-06-25 at 02:03.","The student, Po-Han Huang, submitted this Thesis for approval on 2018-06-25 at 02:08.","This Thesis was approved for publication on 2018-06-25 at 15:24.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12668 on 2018-09-27 at 11:33:39","Made available in DSpace on 2018-09-27T16:45:34Z (GMT). No. of bitstreams: 2 HUANG-THESIS-2018.pdf: 11339483 bytes, checksum: 538ad32f08093c8f042b591e6f822a7d (MD5) LICENSE.txt: 4209 bytes, checksum: 6d984b618e6c62815c7a78e89454431a (MD5) Previous issue date: 2018-06-25","Embargo set by: Seth Robbins for item 107870 Lift date: 2020-09-27T16:45:39Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107870 Lift date: 2020-09-27T16:47:41Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 107870 on 2020-09-28T09:15:22Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/101770"],"dc:language":["en"],"dc:rights":["Copyright 2018 Po-Han Huang"],"dc:subject":["computer vision, deep learning, multi-view stereo, DeepMVS, pattern recognition, 3D reconstruction, depth estimation, machine learning, convolutional neural network"],"dc:title":["DeepMVS: learning multi-view stereopsis"],"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":"2026-07-22T22:24:40Z"}