{"id":"https://openalex.org/W7138458543","doi":"https://doi.org/10.1609/aaai.v40i11.37872","title":"Zero-to-Hero: Empowering Video Appearance Transfer with Zero-Shot Initialization and Holistic Restoration","display_name":"Zero-to-Hero: Empowering Video Appearance Transfer with Zero-Shot Initialization and Holistic Restoration","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138458543","doi":"https://doi.org/10.1609/aaai.v40i11.37872"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i11.37872","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37872","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i11.37872","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054602568","display_name":"Tongtong Su","orcid":"https://orcid.org/0000-0003-4021-6466"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongtong Su","raw_affiliation_strings":["Zhejiang University\nAlibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University\nAlibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373453","display_name":"Chengyu Wang","orcid":"https://orcid.org/0000-0003-3894-2995"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyu Wang","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129752755","display_name":"Haipeng Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haipeng Liao","raw_affiliation_strings":["NingboTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NingboTech University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129717586","display_name":"Jun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Huang","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129695191","display_name":"Dongming Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongming Lu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"9153","last_page":"9161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9041000008583069,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9041000008583069,"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/T11448","display_name":"Face recognition and analysis","score":0.055799998342990875,"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/T11019","display_name":"Image Enhancement Techniques","score":0.010300000198185444,"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/initialization","display_name":"Initialization","score":0.7279000282287598},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6937999725341797},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.6664999723434448},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49799999594688416},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4575999975204468},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43709999322891235},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4341999888420105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230000138282776},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7279000282287598},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6937999725341797},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922999978065491},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4821999967098236},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41850000619888306},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.40529999136924744},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39399999380111694},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.35260000824928284},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2662999927997589}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i11.37872","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37872","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37872","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37872","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37872","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37872","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5229976773262024,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Appearance":[0],"editing":[1,28,50,54,65],"according":[2],"to":[3,18,69,108],"user":[4,21,71],"needs":[5],"is":[6,114],"a":[7,40,74,140,175,189,199,211],"pivotal":[8],"task":[9],"in":[10,87,95,125,153,158],"video":[11,49,127,180],"editing.":[12],"Existing":[13],"text-guided":[14],"methods":[15],"often":[16],"lead":[17],"ambiguities":[19],"regarding":[20],"intentions":[22],"and":[23,77,148,165,201],"restrict":[24],"fine-grained":[25,200],"control":[26],"over":[27],"specific":[29],"aspects":[30],"of":[31,99,191,214],"objects.":[32],"To":[33,90,182],"overcome":[34],"these":[35],"limitations,":[36],"this":[37,62],"paper":[38],"introduces":[39],"novel":[41],"approach":[42],"named":[43],"Zero-to-Hero,":[44,100],"which":[45,113],"focuses":[46],"on":[47],"reference-based":[48],"by":[51,63],"disentangling":[52],"the":[53,84,88,96,105,110,154,169,207],"process":[55],"into":[56],"two":[57],"distinct":[58],"problems.":[59],"It":[60],"achieves":[61],"first":[64,97],"an":[66],"anchor":[67],"frame":[68],"satisfy":[70],"requirements":[72],"as":[73],"reference":[75],"image":[76],"then":[78],"consistently":[79],"propagating":[80],"its":[81],"appearance":[82,93,185],"across":[83],"other":[85],"frames":[86,107],"video.":[89],"achieve":[91],"accurate":[92],"propagation,":[94],"stage":[98],"we":[101,187],"leverage":[102],"correspondences":[103],"within":[104],"original":[106],"guide":[109],"attention":[111,155],"mechanism,":[112],"more":[115],"robust":[116],"than":[117],"previously":[118],"proposed":[119],"optical":[120],"flow":[121],"or":[122],"temporal":[123,149],"modules":[124],"memory-friendly":[126],"generative":[128,177],"models,":[129],"especially":[130],"when":[131],"dealing":[132],"with":[133,162,193,210],"objects":[134],"exhibiting":[135],"large":[136],"motions.":[137],"This":[138],"offers":[139],"solid":[141],"zero-shot":[142],"initialization":[143],"that":[144],"ensures":[145],"both":[146],"accuracy":[147],"consistency.":[150],"However,":[151],"intervention":[152],"mechanism":[156],"results":[157],"compounded":[159],"imaging":[160],"degradation":[161],"unknown":[163],"blurring":[164],"color-missing":[166],"issues.":[167],"Following":[168],"Zero-Stage,":[170],"our":[171],"Hero-Stage":[172],"holistically":[173],"learns":[174],"conditional":[176],"model":[178],"for":[179],"restoration.":[181],"accurately":[183],"evaluate":[184],"consistency,":[186],"construct":[188],"set":[190],"videos":[192],"multiple":[194],"appearances":[195],"using":[196],"Blender,":[197],"enabling":[198],"deterministic":[202],"evaluation.":[203],"Our":[204],"method":[205],"outperforms":[206],"best-performing":[208],"baseline":[209],"PSNR":[212],"improvement":[213],"2.6":[215],"dB.":[216]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}