{"id":"https://openalex.org/W4403571327","doi":"https://doi.org/10.1109/iccv51701.2025.01739","title":"FlexGen: Flexible Multi-View Generation from Text and Image Inputs","display_name":"FlexGen: Flexible Multi-View Generation from Text and Image Inputs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4403571327","doi":"https://doi.org/10.1109/iccv51701.2025.01739"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01739","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.10745","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101482591","display_name":"Xinli Xu","orcid":"https://orcid.org/0000-0002-6392-9437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinli Xu","raw_affiliation_strings":["HKUST(GZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST(GZ)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024461965","display_name":"Wenhang Ge","orcid":"https://orcid.org/0009-0000-8726-7768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhang Ge","raw_affiliation_strings":["HKUST(GZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST(GZ)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101419029","display_name":"Jiantao Lin","orcid":"https://orcid.org/0000-0001-5705-2299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiantao Lin","raw_affiliation_strings":["HKUST(GZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST(GZ)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102773609","display_name":"Jiawei Feng","orcid":"https://orcid.org/0000-0003-1469-726X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Feng","raw_affiliation_strings":["HKUST(GZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST(GZ)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091022458","display_name":"Lie Xu","orcid":"https://orcid.org/0000-0002-1808-8608"},"institutions":[{"id":"https://openalex.org/I98070013","display_name":"Quincy University","ror":"https://ror.org/043d4x248","country_code":"US","type":"education","lineage":["https://openalex.org/I98070013"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lie Xu","raw_affiliation_strings":["Quwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quwan","institution_ids":["https://openalex.org/I98070013"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101492535","display_name":"Haiyun Zhao","orcid":"https://orcid.org/0000-0002-8920-9016"},"institutions":[{"id":"https://openalex.org/I98070013","display_name":"Quincy University","ror":"https://ror.org/043d4x248","country_code":"US","type":"education","lineage":["https://openalex.org/I98070013"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanfeng Zhao","raw_affiliation_strings":["Quwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quwan","institution_ids":["https://openalex.org/I98070013"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111110986","display_name":"Shunsi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I98070013","display_name":"Quincy University","ror":"https://ror.org/043d4x248","country_code":"US","type":"education","lineage":["https://openalex.org/I98070013"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shunsi Zhang","raw_affiliation_strings":["Quwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quwan","institution_ids":["https://openalex.org/I98070013"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101938761","display_name":"Ying-Cong Chen","orcid":"https://orcid.org/0000-0002-9565-8205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying-Cong Chen","raw_affiliation_strings":["HKUST(GZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST(GZ)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00057491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18714","last_page":"18724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9939000010490417,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9939000010490417,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9861000180244446,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9577999711036682,"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/image","display_name":"Image (mathematics)","score":0.6112147569656372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5752135515213013},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47042083740234375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4079786539077759}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6112147569656372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5752135515213013},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47042083740234375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4079786539077759}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01739","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:2410.10745","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.10745","pdf_url":"https://arxiv.org/pdf/2410.10745","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.10745","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.10745","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.10745","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.10745","pdf_url":"https://arxiv.org/pdf/2410.10745","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"introduce":[4],"FlexGen,":[5],"a":[6,19,23,147],"flexible":[7,165],"framework":[8],"designed":[9],"to":[10,51,99,110,114],"generate":[11,52,94,115],"controllable":[12,33,106],"and":[13,117,129,134,164,173],"consistent":[14],"multi-view":[15,34,67,95,152],"images,":[16,68],"conditioned":[17],"on":[18,39],"single-view":[20],"image,":[21],"or":[22,26],"text":[24,41,54,72,112],"prompt,":[25],"both.":[27],"FlexGen":[28,103],"tackles":[29],"the":[30,45,83,100],"challenges":[31],"of":[32,49,61],"synthesis":[35],"through":[36],"additional":[37],"conditioning":[38],"3D-aware":[40,53,76],"annotations.":[42,55],"We":[43],"utilize":[44],"strong":[46],"reasoning":[47],"capabilities":[48],"GPT-4V":[50,69],"By":[56,81],"analyzing":[57],"four":[58],"orthogonal":[59],"views":[60],"an":[62],"object":[63],"arranged":[64],"as":[65,127],"tiled":[66],"can":[70,93,123],"produce":[71],"annotations":[73],"that":[74,97,139],"include":[75],"information":[77],"with":[78,86],"spatial":[79],"relationship.":[80],"integrating":[82],"control":[84],"signal":[85],"proposed":[87],"adaptive":[88],"dual-control":[89],"module,":[90],"our":[91,140],"model":[92],"images":[96],"correspond":[98],"specified":[101],"text.":[102],"supports":[104],"multiple":[105,144],"capabilities,":[107],"allowing":[108],"users":[109,122],"modify":[111],"prompts":[113],"reasonable":[116],"corresponding":[118],"unseen":[119],"parts.":[120],"Additionally,":[121],"influence":[124],"attributes":[125],"such":[126],"appearance":[128],"material":[130],"properties,":[131],"including":[132,169],"metallic":[133],"roughness.":[135],"Extensive":[136],"experiments":[137],"demonstrate":[138],"approach":[141],"offers":[142],"enhanced":[143],"controllability,":[145],"marking":[146],"significant":[148],"advancement":[149],"over":[150],"existing":[151],"diffusion":[153],"models.":[154],"This":[155],"work":[156],"has":[157],"substantial":[158],"implications":[159],"for":[160],"fields":[161],"requiring":[162],"rapid":[163],"3D":[166],"content":[167],"creation,":[168],"game":[170],"development,":[171],"animation,":[172],"virtual":[174],"reality.":[175],"Project":[176],"page:":[177],"https://xxu068.github.io/flexgen.github.io/.":[178]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}
