{"id":"https://openalex.org/W4416176398","doi":"https://doi.org/10.1109/iccv51701.2025.01688","title":"Anchor Token Matching: Implicit Structure Locking for Training-Free AR Image Editing","display_name":"Anchor Token Matching: Implicit Structure Locking for Training-Free AR Image Editing","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416176398","doi":"https://doi.org/10.1109/iccv51701.2025.01688"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01688","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/2504.10434","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070092416","display_name":"Taihang Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taihang Hu","raw_affiliation_strings":["VCIP, College of Computer Science, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, College of Computer Science, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092862243","display_name":"Linxuan Li","orcid":"https://orcid.org/0009-0008-7745-2618"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linxuan Li","raw_affiliation_strings":["VCIP, College of Computer Science, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, College of Computer Science, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437056","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-7870-9998"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Computer Vision Center, Universitat Autònoma de Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center, Universitat Autònoma de Barcelona","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665185","display_name":"Yaxing Wang","orcid":"https://orcid.org/0000-0001-6609-1003"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaxing Wang","raw_affiliation_strings":["NKIARI, Shenzhen Futian"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NKIARI, Shenzhen Futian","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614247","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-2373-8799"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["VCIP, College of Computer Science, Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, College of Computer Science, Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037131575","display_name":"Ming\u2010Ming Cheng","orcid":"https://orcid.org/0000-0001-5550-8758"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["NKIARI, Shenzhen Futian"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NKIARI, Shenzhen Futian","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18166","last_page":"18176"},"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":0.7364000082015991,"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":0.7364000082015991,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.06710000336170197,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.011500000022351742,"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-editing","display_name":"Image editing","score":0.7577999830245972},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5303000211715698},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4968999922275543},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.475600004196167},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.46950000524520874},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.412200003862381},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.40310001373291016},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.3310000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342000246047974},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7577999830245972},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4968999922275543},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.46950000524520874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45980000495910645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.40310001373291016},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3310000002384186},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25600001215934753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01688","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:2504.10434","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.10434","pdf_url":"https://arxiv.org/pdf/2504.10434","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.10434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.10434","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:2504.10434","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.10434","pdf_url":"https://arxiv.org/pdf/2504.10434","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6785956370","display_name":null,"funder_award_id":"62225604","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8137314104","display_name":null,"funder_award_id":"62202243","funder_id":"https://openalex.org/F4320307500","funder_display_name":"Youth Foundation"}],"funders":[{"id":"https://openalex.org/F4320307500","display_name":"Youth Foundation","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321595","display_name":"Federaci\u00f3n Espa\u00f1ola de Enfermedades Raras","ror":"https://ror.org/0348bpk17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416176398.pdf","grobid_xml":"https://content.openalex.org/works/W4416176398.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"generation":[1,30],"has":[2],"seen":[3],"groundbreaking":[4],"advancements":[5],"with":[6,119],"diffusion":[7,33,41,186],"models,":[8],"enabling":[9],"high-fidelity":[10],"synthesis":[11],"and":[12,67,80,159,175,187],"precise":[13],"image":[14,74,178],"editing":[15,37,95,142,166],"through":[16,122],"cross-attention":[17],"manipulation.":[18],"Recently,":[19],"autoregressive":[20,188],"(AR)":[21],"models":[22,42,49,59],"have":[23],"re-emerged":[24],"as":[25],"powerful":[26],"alternatives,":[27],"leveraging":[28],"next-token":[29],"to":[31,44,47,51,164],"match":[32],"models.":[34,100,190],"However,":[35],"existing":[36],"techniques":[38],"designed":[39],"for":[40,97,173],"fail":[43],"translate":[45],"directly":[46],"AR":[48,58,98],"due":[50],"fundamental":[52],"differences":[53],"in":[54,134],"structural":[55,71,112,132],"control.":[56],"Specifically,":[57],"suffer":[60],"from":[61],"spatial":[62],"poverty":[63],"of":[64,70],"attention":[65,106],"maps":[66],"sequential":[68],"accumulation":[69],"errors":[72],"during":[73],"editing,":[75,179],"which":[76],"disrupt":[77],"object":[78],"layouts":[79],"global":[81],"consistency.":[82],"In":[83],"this":[84],"work,":[85],"we":[86],"introduce":[87],"Implicit":[88],"Structure":[89],"Locking":[90],"(ISLock),":[91],"the":[92,123,171,182],"first":[93],"training-free":[94],"strategy":[96],"visual":[99],"Rather":[101],"than":[102],"relying":[103],"on":[104],"explicit":[105],"manipulation":[107],"or":[108,162],"fine-tuning,":[109],"ISLock":[110,139,151],"preserves":[111],"blueprints":[113],"by":[114],"dynamically":[115],"aligning":[116],"self-attention":[117],"patterns":[118],"reference":[120],"images":[121],"Anchor":[124],"Token":[125],"Matching":[126],"(ATM)":[127],"protocol.":[128],"By":[129],"implicitly":[130],"enforcing":[131],"consistency":[133],"latent":[135],"space,":[136],"our":[137],"method":[138],"enables":[140],"structure-aware":[141],"while":[143],"maintaining":[144],"generative":[145,189],"autonomy.":[146],"Extensive":[147],"experiments":[148],"demonstrate":[149],"that":[150],"achieves":[152],"high-quality,":[153],"structure-consistent":[154],"edits":[155],"without":[156],"additional":[157],"training":[158],"is":[160],"superior":[161],"comparable":[163],"conventional":[165],"techniques.":[167],"Our":[168],"findings":[169],"pioneer":[170],"way":[172],"efficient":[174],"flexible":[176],"AR-based":[177],"further":[180],"bridging":[181],"performance":[183],"gap":[184],"between":[185],"The":[191],"code":[192],"will":[193],"be":[194],"publicly":[195],"available":[196],"at":[197],"https://github.com/hutaiHang/ATM":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}