{"id":"https://openalex.org/W4409796242","doi":"https://doi.org/10.1109/tpami.2025.3562237","title":"AnyDoor: Zero-Shot Image Customization With Region-to-Region Reference","display_name":"AnyDoor: Zero-Shot Image Customization With Region-to-Region Reference","publication_year":2025,"publication_date":"2025-04-25","ids":{"openalex":"https://openalex.org/W4409796242","doi":"https://doi.org/10.1109/tpami.2025.3562237","pmid":"https://pubmed.ncbi.nlm.nih.gov/40279229"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3562237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3562237","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120313167","display_name":"Xi Chen","orcid":"https://orcid.org/0009-0008-5008-4720"},"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":true,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019994258","display_name":"Lianghua Huang","orcid":"https://orcid.org/0000-0002-9686-9354"},"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":"Lianghua Huang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101981779","display_name":"Liu Yu","orcid":"https://orcid.org/0000-0002-2900-0288"},"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"]},{"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":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China","Department of Computer Science, The University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103003762","display_name":"Yujun Shen","orcid":"https://orcid.org/0000-0003-3801-6705"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Shen","raw_affiliation_strings":["Ant Group, Hangzhou, China","Ant Group, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]},{"raw_affiliation_string":"Ant Group, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911374","display_name":"Deli Zhao","orcid":"https://orcid.org/0000-0002-8838-578X"},"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":"Deli Zhao","raw_affiliation_strings":["Alibaba Group, Hangzhou, China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078109015","display_name":"Hengshuang Zhao","orcid":"https://orcid.org/0000-0001-8277-2706"},"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":"Hengshuang Zhao","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5120313167"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":1.2784,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79101949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"47","issue":"8","first_page":"6480","last_page":"6495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9779999852180481,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9779999852180481,"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":0.9524999856948853,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9451000094413757,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6497704982757568},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6445428729057312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6098493337631226},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5651928186416626},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5024981498718262},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.45742902159690857},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40680375695228577}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6497704982757568},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6445428729057312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6098493337631226},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5651928186416626},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5024981498718262},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.45742902159690857},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40680375695228577},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3562237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3562237","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40279229","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40279229","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1772076007","https://openalex.org/W1861492603","https://openalex.org/W2017745767","https://openalex.org/W2133665775","https://openalex.org/W2740667773","https://openalex.org/W2889986507","https://openalex.org/W2948672349","https://openalex.org/W2981464166","https://openalex.org/W2982695696","https://openalex.org/W2982723417","https://openalex.org/W3025800305","https://openalex.org/W3034684802","https://openalex.org/W3158120491","https://openalex.org/W3171358896","https://openalex.org/W3173998882","https://openalex.org/W3199003182","https://openalex.org/W3216352822","https://openalex.org/W4214588164","https://openalex.org/W4229682756","https://openalex.org/W4312336332","https://openalex.org/W4312698476","https://openalex.org/W4312868348","https://openalex.org/W4312933868","https://openalex.org/W4312966374","https://openalex.org/W4313065289","https://openalex.org/W4319300361","https://openalex.org/W4386057725","https://openalex.org/W4386072096","https://openalex.org/W4386075528","https://openalex.org/W4386075533","https://openalex.org/W4386075993","https://openalex.org/W4386076425","https://openalex.org/W4386083141","https://openalex.org/W4386083144","https://openalex.org/W4386083151","https://openalex.org/W4387968695","https://openalex.org/W4389539271","https://openalex.org/W4390872677","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390873331","https://openalex.org/W4390873799","https://openalex.org/W4390874575","https://openalex.org/W4394596511","https://openalex.org/W4401023551","https://openalex.org/W4402727781","https://openalex.org/W4402753775","https://openalex.org/W4402774219","https://openalex.org/W4402782221","https://openalex.org/W4402952275","https://openalex.org/W4403791610","https://openalex.org/W4404024902","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6765779288","https://openalex.org/W6791353385","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6841755765","https://openalex.org/W6849177959","https://openalex.org/W6849599665","https://openalex.org/W6850995708","https://openalex.org/W6851510481","https://openalex.org/W6851513319","https://openalex.org/W6851800889","https://openalex.org/W6851932778","https://openalex.org/W6852885189","https://openalex.org/W6852985244","https://openalex.org/W6853067783","https://openalex.org/W6853219534","https://openalex.org/W6853578883","https://openalex.org/W6854325678","https://openalex.org/W6854511533","https://openalex.org/W6855771293","https://openalex.org/W6855949956","https://openalex.org/W6869409315","https://openalex.org/W6869548429"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"AnyDoor,":[3],"a":[4,49,58,140,165],"diffusion-based":[5],"image":[6,69,170,191],"generator":[7],"with":[8,21,89,116,168],"the":[9,45,66,75,80,86,111,136,152,160,173,177,183,211],"power":[10],"to":[11,15,40,73,96,122,144,164,221],"teleport":[12],"target":[13,81,181],"objects":[14],"new":[16],"scenes":[17],"at":[18,44],"user-specified":[19],"locations":[20],"desired":[22],"shapes.":[23],"Instead":[24],"of":[25,57,79,139,154,162,176,185],"tuning":[26],"parameters":[27],"for":[28],"each":[29],"object,":[30,142],"our":[31],"model":[32,146,198],"is":[33],"trained":[34],"only":[35],"once":[36],"and":[37,148,180,190,215],"effortlessly":[38],"generalizes":[39],"diverse":[41],"object-scene":[42],"combinations":[43],"inference":[46],"stage.":[47],"Such":[48],"challenging":[50],"zero-shot":[51],"setting":[52],"requires":[53],"an":[54],"adequate":[55],"characterization":[56],"certain":[59],"object.":[60,82],"To":[61],"this":[62],"end,":[63],"we":[64,84,129,157,205],"leverage":[65],"powerful":[67],"self-supervised":[68],"encoder":[70],"(i.e.,":[71,134],"DINOv2)":[72],"extract":[74],"discriminative":[76],"dentity":[77],"feature":[78,88],"Besides,":[83],"complement":[85],"identity":[87],"detail":[90],"features,":[91],"which":[92],"are":[93],"carefully":[94],"designed":[95],"maintain":[97],"appearance":[98],"details":[99],"yet":[100],"allow":[101],"versatile":[102],"local":[103],"variations":[104],"(e.g.,":[105],"lighting,":[106],"orientation,":[107],"posture,":[108],"etc.),":[109],"supporting":[110],"object":[112,155,186,188],"in":[113],"favorably":[114],"blending":[115],"different":[117,174],"surroundings.":[118],"We":[119],"further":[120,158],"propose":[121],"borrow":[123],"knowledge":[124],"from":[125,151],"video":[126],"datasets,":[127],"where":[128],"can":[130],"observe":[131],"various":[132],"forms":[133],"along":[135],"time":[137],"axis)":[138],"single":[141],"leading":[143],"stronger":[145],"generalizability":[147],"robustness.":[149],"Starting":[150],"task":[153],"insertion,":[156,187],"extend":[159],"framework":[161],"AnyDoor":[163],"general":[166],"solution":[167],"region-to-region":[169],"reference.":[171],"With":[172],"definitions":[175],"source":[178],"region":[179],"region,":[182],"tasks":[184],"removal,":[189],"variation":[192],"could":[193],"be":[194],"integrated":[195],"into":[196],"one":[197],"without":[199],"introducing":[200],"extra":[201],"parameters.":[202],"In":[203],"addition,":[204],"investigate":[206],"incorporating":[207],"other":[208],"conditions":[209],"like":[210],"mask,":[212],"pose":[213],"skeleton,":[214],"depth":[216],"map":[217],"as":[218],"additional":[219],"guidance":[220],"achieve":[222],"more":[223],"controllable":[224],"generation.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
