{"id":"https://openalex.org/W4405096525","doi":"https://doi.org/10.1109/iccv51701.2025.01520","title":"Mv-Adapter: Multi-View Consistent Image Generation Made Easy","display_name":"Mv-Adapter: Multi-View Consistent Image Generation Made Easy","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405096525","doi":"https://doi.org/10.1109/iccv51701.2025.01520"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.03632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090539958","display_name":"Zehuan Huang","orcid":"https://orcid.org/0000-0003-4111-7064"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehuan Huang","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102364152","display_name":"Yuan\u2013Chen Guo","orcid":"https://orcid.org/0000-0001-6164-8343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan-Chen Guo","raw_affiliation_strings":["VAST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VAST","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324823","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0002-3626-2286"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066573999","display_name":"Ran Yi","orcid":"https://orcid.org/0000-0003-3266-3805"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Yi","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhuang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091525681","display_name":"Yan\u2010Pei Cao","orcid":"https://orcid.org/0000-0002-0416-4374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan-Pei Cao","raw_affiliation_strings":["VAST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VAST","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110516350","display_name":"Lu Sheng","orcid":"https://orcid.org/0009-0001-2570-0690"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Sheng","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16377","last_page":"16387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10888","display_name":"Augmented Reality Applications","score":0.5550000071525574,"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"}},"topics":[{"id":"https://openalex.org/T10888","display_name":"Augmented Reality Applications","score":0.5550000071525574,"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/adapter","display_name":"Adapter (computing)","score":0.7877477407455444},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.510006308555603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49876880645751953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35890913009643555},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1891653835773468}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7877477407455444},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.510006308555603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49876880645751953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35890913009643555},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1891653835773468}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.03632","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03632","pdf_url":"https://arxiv.org/pdf/2412.03632","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.03632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.03632","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.03632","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03632","pdf_url":"https://arxiv.org/pdf/2412.03632","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6078352744","display_name":null,"funder_award_id":"62132001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W3184035966","https://openalex.org/W2485605994"],"abstract_inverted_index":{"Existing":[0],"multi-view":[1,57,172,209],"image":[2,36,58,210],"generation":[3,167,173],"methods":[4],"often":[5],"make":[6],"invasive":[7],"modifications":[8],"to":[9,19,39,129,138,192,218],"pre-trained":[10,98,136],"text-to-image":[11],"(T2I)":[12],"models":[13,28,70,137],"and":[14,29,32,42,60,71,91,122,156,164,168,182,185,212,222],"require":[15],"full":[16],"fine-tuning,":[17],"leading":[18],"(1)":[20],"high":[21],"computational":[22],"costs,":[23],"especially":[24],"with":[25],"large":[26],"base":[27],"high-resolution":[30],"images,":[31],"(2)":[33],"degradation":[34],"in":[35,97],"quality":[37,206],"due":[38,217],"optimization":[40],"difficulties":[41],"scarce":[43],"high-quality":[44],"3D":[45,107,142,166],"data.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50,113,145],"propose":[51],"the":[52,76,93,106,111,127,131,135,140],"first":[53],"adapter-based":[54],"solution":[55],"for":[56,208],"generation,":[59,195,211],"introduce":[61,114],"MV-Adapter,":[62],"a":[63,147,204],"versatile":[64],"plug-and-play":[65],"adapter":[66,128],"that":[67,117,151,201],"enhances":[68],"T2I":[69],"their":[72],"derivatives":[73],"without":[74],"altering":[75],"original":[77],"network":[78],"structure":[79],"or":[80],"feature":[81],"space.":[82],"By":[83],"updating":[84],"fewer":[85],"parameters,":[86],"MV-Adapter":[87,170,202],"enables":[88],"efficient":[89],"training":[90],"preserves":[92],"prior":[94],"knowledge":[95,109],"embedded":[96],"models,":[99],"mitigating":[100],"overfitting":[101],"risks.":[102],"To":[103],"efficiently":[104],"model":[105,139],"geometric":[108,157],"within":[110],"adapter,":[112],"innovative":[115],"designs":[116],"include":[118],"duplicated":[119],"self-attention":[120],"layers":[121],"parallel":[123],"attention":[124],"architecture,":[125],"enabling":[126,196],"inherit":[130],"powerful":[132],"priors":[133],"of":[134],"novel":[141],"knowledge.":[143],"Moreover,":[144],"present":[146],"unified":[148],"condition":[149],"encoder":[150],"seamlessly":[152],"integrates":[153],"camera":[154],"parameters":[155],"information,":[158],"facilitating":[159],"applications":[160],"such":[161],"as":[162],"text-":[163],"image-based":[165],"texturing.":[169],"achieves":[171],"at":[174],"768":[175],"resolution":[176],"on":[177],"Stable":[178],"Diffusion":[179],"XL":[180],"(SDXL),":[181],"demonstrates":[183],"adaptability":[184,221],"versatility.":[186,223],"It":[187],"can":[188],"also":[189],"be":[190],"extended":[191],"arbitrary":[193],"view":[194],"broader":[197],"applications.":[198],"We":[199],"demonstrate":[200],"sets":[203],"new":[205,215],"standard":[207],"opens":[213],"up":[214],"possibilities":[216],"its":[219],"efficiency,":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}