{"id":"https://openalex.org/W4414984169","doi":"https://doi.org/10.1109/iccv51701.2025.01490","title":"CharaConsist: Fine-Grained Consistent Character Generation","display_name":"CharaConsist: Fine-Grained Consistent Character Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414984169","doi":"https://doi.org/10.1109/iccv51701.2025.01490"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01490","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/2507.11533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mengyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyu Wang","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Henghui Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Henghui Ding","raw_affiliation_strings":["Institute of Big Data, Fudan University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Big Data, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianing Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianing Peng","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113789394","display_name":"Yao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059381569","display_name":"Yunpeng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I36169673","display_name":"Alstom (France)","ror":"https://ror.org/00t4db855","country_code":"FR","type":"company","lineage":["https://openalex.org/I36169673"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yunpeng Chen","raw_affiliation_strings":["Alkaid Pte. Ltd.,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alkaid Pte. Ltd.,Singapore","institution_ids":["https://openalex.org/I36169673"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yunchao Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchao Wei","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.2396796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16058","last_page":"16067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8325999975204468,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8325999975204468,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8234999775886536,"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/merge","display_name":"Merge (version control)","score":0.6251999735832214},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.44769999384880066},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.40070000290870667},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3903999924659729},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3068000078201294}],"concepts":[{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6043999791145325},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4417000114917755},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38679999113082886},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2605000138282776}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01490","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:2507.11533","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.11533","pdf_url":"https://arxiv.org/pdf/2507.11533","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.11533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.11533","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2507.11533","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.11533","pdf_url":"https://arxiv.org/pdf/2507.11533","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4316271325","display_name":null,"funder_award_id":"2024XKRC082","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7434382074","display_name":null,"funder_award_id":"92470203,62472104","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"text-to-image":[1,136],"generation,":[2],"producing":[3],"a":[4,21,116,165],"series":[5],"of":[6,32,92,109,150,168],"consistent":[7,49,131],"contents":[8],"that":[9,37],"preserve":[10],"the":[11,30,41,58,93,107,129,147],"same":[12],"identity":[13,67],"is":[14,128],"highly":[15],"valuable":[16],"for":[17,101,135],"real-world":[18,169],"applications.":[19],"Although":[20],"few":[22],"works":[23],"have":[24],"explored":[25],"training-free":[26],"methods":[27],"to":[28,47,141,156,164],"enhance":[29],"consistency":[31,100],"generated":[33],"subjects,":[34],"we":[35,77],"observe":[36],"they":[38,45],"suffer":[39],"from":[40],"following":[42],"problems.":[43],"First,":[44],"fail":[46],"maintain":[48,142],"background":[50],"details,":[51],"which":[52,80],"limits":[53],"their":[54],"applicability.":[55],"Furthermore,":[56],"when":[57],"foreground":[59,94,103],"character":[60,111],"undergoes":[61],"large":[62],"motion":[63],"variations,":[64],"inconsistencies":[65],"in":[66,112,120],"and":[68,84,95,104],"clothing":[69],"details":[70],"become":[71],"evident.":[72],"To":[73],"address":[74],"these":[75],"problems,":[76],"propose":[78],"CharaConsist,":[79],"employs":[81],"point-tracking":[82],"attention":[83],"adaptive":[85],"token":[86],"merge":[87],"along":[88],"with":[89,146],"decoupled":[90],"control":[91],"background.":[96],"CharaConsist":[97,127],"enables":[98,154],"fine-grained":[99,143],"both":[102],"background,":[105],"supporting":[106],"generation":[108,132],"one":[110],"continuous":[113],"shots":[114,122],"within":[115],"fixed":[117],"scene":[118],"or":[119],"discrete":[121],"across":[123],"different":[124],"scenes.":[125],"Moreover,":[126],"first":[130],"method":[133],"tailored":[134],"DiT":[137],"model.":[138],"Its":[139],"ability":[140],"consistency,":[144],"combined":[145],"larger":[148],"capacity":[149],"latest":[151],"base":[152],"model,":[153],"it":[155],"produce":[157],"high-quality":[158],"visual":[159],"outputs,":[160],"broadening":[161],"its":[162],"applicability":[163],"wider":[166],"range":[167],"scenarios.":[170],"The":[171],"source":[172],"code":[173],"has":[174],"been":[175],"released":[176],"at":[177],"https://github.com/Murray-Wang/CharaConsist":[178]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-09T00:00:00"}