{"id":"https://openalex.org/W4406192895","doi":"https://doi.org/10.1109/iccv51701.2025.01342","title":"MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers","display_name":"MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406192895","doi":"https://doi.org/10.1109/iccv51701.2025.01342"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01342","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/2501.03931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009874821","display_name":"Yuechen Zhang","orcid":"https://orcid.org/0009-0000-9112-0216"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuechen Zhang","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047380396","display_name":"Yaoyang Liu","orcid":"https://orcid.org/0000-0002-0942-9650"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yaoyang Liu","raw_affiliation_strings":["HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751857","display_name":"Bin Xia","orcid":"https://orcid.org/0000-0002-5583-3275"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bin Xia","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025923008","display_name":"Bohao Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bohao Peng","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zexin Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexin Yan","raw_affiliation_strings":["CMU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011148671","display_name":"Eric Lo","orcid":"https://orcid.org/0000-0003-2679-3945"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Eric Lo","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052856441","display_name":"Jiaya Jia","orcid":"https://orcid.org/0000-0002-1246-553X"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaya Jia","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]}],"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":"14464","last_page":"14474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9771999716758728,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9771999716758728,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9733999967575073,"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/magic","display_name":"MAGIC (telescope)","score":0.6148502826690674},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5159803032875061},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46009817719459534},{"id":"https://openalex.org/keywords/video-recording","display_name":"Video recording","score":0.412563681602478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38964974880218506},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.35807377099990845},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.19276821613311768},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1921100616455078},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16325214505195618},{"id":"https://openalex.org/keywords/astronomy","display_name":"Astronomy","score":0.10349422693252563},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0513778030872345}],"concepts":[{"id":"https://openalex.org/C2777704519","wikidata":"https://www.wikidata.org/wiki/Q45732","display_name":"MAGIC (telescope)","level":2,"score":0.6148502826690674},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5159803032875061},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46009817719459534},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.412563681602478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38964974880218506},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.35807377099990845},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.19276821613311768},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1921100616455078},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16325214505195618},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.10349422693252563},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0513778030872345}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01342","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:2501.03931","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.03931","pdf_url":"https://arxiv.org/pdf/2501.03931","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.03931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.03931","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:2501.03931","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.03931","pdf_url":"https://arxiv.org/pdf/2501.03931","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5025751825","display_name":null,"funder_award_id":"IITP-2026-RS-2022-00156353","funder_id":"https://openalex.org/F4320326646","funder_display_name":"Genome Alberta"},{"id":"https://openalex.org/G5954340356","display_name":null,"funder_award_id":"RS-202300209125","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320326646","display_name":"Genome Alberta","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W2748952813","https://openalex.org/W1531601525"],"abstract_inverted_index":{"We":[0],"present":[1],"MagicMirror,":[2],"a":[3,65,78,92],"framework":[4],"for":[5,86],"generating":[6],"identity-preserved":[7],"videos":[8],"with":[9,50,82,100,112],"cinematic-level":[10],"quality":[11],"and":[12,74,90,128],"dynamic":[13],"motion.":[14],"While":[15],"recent":[16],"advances":[17],"in":[18,26],"video":[19,101],"diffusion":[20],"models":[21],"have":[22],"shown":[23],"impressive":[24],"capabilities":[25],"text-to-video":[27],"generation,":[28],"maintaining":[29],"consistent":[30],"identity":[31,48,73,88,98,110],"while":[32,121],"producing":[33],"natural":[34,113],"motion":[35,51],"remains":[36],"challenging.":[37],"Previous":[38],"methods":[39,117],"either":[40],"require":[41],"person-specific":[42],"fine-tuning":[43],"or":[44],"struggle":[45],"to":[46],"balance":[47],"preservation":[49],"diversity.":[52],"Built":[53],"upon":[54],"Video":[55],"Diffusion":[56],"Transformers,":[57],"our":[58],"method":[59],"introduces":[60],"three":[61],"key":[62],"components:":[63],"(1)":[64],"dual-branch":[66],"facial":[67],"feature":[68],"extractor":[69],"that":[70,106],"captures":[71],"both":[72],"structural":[75],"features,":[76],"(2)":[77],"lightweight":[79],"cross-modal":[80],"adapter":[81],"Conditioned":[83],"Adaptive":[84],"Normalization":[85],"efficient":[87],"integration,":[89],"(3)":[91],"two-stage":[93],"training":[94],"strategy":[95],"combining":[96],"synthetic":[97],"pairs":[99],"data.":[102],"Extensive":[103],"experiments":[104],"demonstrate":[105],"MagicMirror":[107],"effectively":[108],"balances":[109],"consistency":[111],"motion,":[114],"outperforming":[115],"existing":[116],"across":[118],"multiple":[119],"metrics":[120],"requiring":[122],"minimal":[123],"parameters":[124],"added.":[125],"The":[126],"code":[127],"model":[129],"will":[130],"be":[131],"made":[132],"publicly":[133],"available.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
