{"id":"https://openalex.org/W7160235468","doi":"https://doi.org/10.1109/wacv61042.2026.00557","title":"ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points","display_name":"ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160235468","doi":"https://doi.org/10.1109/wacv61042.2026.00557"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135283869","display_name":"Ryota Okumura","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Okumura","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078203902","display_name":"Kaede Shiohara","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaede Shiohara","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135380148","display_name":"Toshihiko Yamasaki","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihiko Yamasaki","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57217543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5744","last_page":"5753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.2948000133037567,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.2948000133037567,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12219999730587006,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.10329999774694443,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vanishing-point","display_name":"Vanishing point","score":0.4535999894142151},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.30059999227523804},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.2955000102519989},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.275299996137619},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27379998564720154}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4702000021934509},{"id":"https://openalex.org/C99404194","wikidata":"https://www.wikidata.org/wiki/Q163362","display_name":"Vanishing point","level":3,"score":0.4535999894142151},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33410000801086426},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4222522974014282,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1968256263","https://openalex.org/W1981934656","https://openalex.org/W1989231886","https://openalex.org/W2010360724","https://openalex.org/W2115340290","https://openalex.org/W2155195832","https://openalex.org/W2155880278","https://openalex.org/W2599231600","https://openalex.org/W2962785568","https://openalex.org/W3175237403","https://openalex.org/W3216983733","https://openalex.org/W4221145452","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4386075501","https://openalex.org/W4386076027","https://openalex.org/W4389347530","https://openalex.org/W4390873054","https://openalex.org/W4394625844","https://openalex.org/W4401906744","https://openalex.org/W4402753971","https://openalex.org/W4402754201","https://openalex.org/W4402754249","https://openalex.org/W4404783794"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"text-to-image":[1],"models,":[2],"such":[3,130],"as":[4,131],"Stable":[5],"Diffusion,":[6],"have":[7],"achieved":[8],"impressive":[9],"visual":[10,112],"quality,":[11],"yet":[12],"they":[13],"often":[14],"suffer":[15],"from":[16,86],"geometric":[17,92,108],"inconsistencies":[18,70],"that":[19,52,94,125],"undermine":[20],"the":[21,116],"structural":[22,83],"realism":[23],"of":[24,36],"generated":[25,72],"scenes.":[26,59],"One":[27],"prominent":[28],"issue":[29],"is":[30,120],"vanishing":[31,68],"point":[32,69],"inconsistency,":[33],"where":[34],"projections":[35],"parallel":[37],"lines":[38],"fail":[39],"to":[40,48,115],"converge":[41],"correctly":[42],"in":[43,57,71],"2D":[44],"space.":[45],"This":[46,118],"leads":[47],"structurally":[49],"implausible":[50],"geometry":[51],"degrades":[53],"spatial":[54,128],"realism,":[55],"especially":[56],"architectural":[58],"We":[60,89],"propose":[61],"ControlVP,":[62],"a":[63,77],"user-guided":[64],"framework":[65],"for":[66,123],"correcting":[67],"images.":[73],"Our":[74,104],"approach":[75],"extends":[76],"pre-trained":[78],"diffusion":[79],"model":[80],"by":[81],"incorporating":[82],"guidance":[84],"derived":[85],"building":[87],"contours.":[88],"also":[90],"introduce":[91],"constraints":[93],"explicitly":[95],"encourage":[96],"alignment":[97],"between":[98],"image":[99],"edges":[100],"and":[101,136],"perspective":[102],"cues.":[103],"method":[105],"enhances":[106],"global":[107],"consistency":[109],"while":[110],"maintaining":[111],"fidelity":[113],"comparable":[114],"baselines.":[117],"capability":[119],"particularly":[121],"valuable":[122],"applications":[124],"require":[126],"accurate":[127],"structure,":[129],"image-to-3D":[132],"reconstruction.":[133],"The":[134],"dataset":[135],"source":[137],"code":[138],"are":[139],"available":[140],"at":[141],"https://github.com/RyotaOkumura/ControlVP.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}