{"id":"https://openalex.org/W7137950349","doi":"https://doi.org/10.1609/aaai.v40i11.37869","title":"Object Fusion via Diffusion Time-step for Customized Image Editing with Single Example","display_name":"Object Fusion via Diffusion Time-step for Customized Image Editing with Single Example","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137950349","doi":"https://doi.org/10.1609/aaai.v40i11.37869"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i11.37869","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37869","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.v40i11.37869","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129751412","display_name":"Xue Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xue Song","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716479","display_name":"Zhongqi Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhongqi Yue","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016170160","display_name":"Jiequan Cui","orcid":"https://orcid.org/0000-0003-2422-7851"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiequan Cui","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722115","display_name":"Hanwang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129704666","display_name":"Jingjing Chen","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":"Jingjing Chen","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University\nInstitute of Trustworthy Embodied AI, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University\nInstitute of Trustworthy Embodied AI, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":"9127","last_page":"9134"},"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":0.6816999912261963,"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":0.6816999912261963,"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":0.0851999968290329,"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/T11094","display_name":"Face Recognition and Perception","score":0.03370000049471855,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6571999788284302},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6097999811172485},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5199000239372253},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.48669999837875366},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.45730000734329224},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4553000032901764},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4551999866962433},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4544000029563904},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.44760000705718994}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562999725341797},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6672000288963318},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6571999788284302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6528000235557556},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6097999811172485},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.48669999837875366},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4551999866962433},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i11.37869","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37869","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/37869","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37869","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.v40i11.37869","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37869","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,104],"tackle":[1],"the":[2,19,36,42,45,67,89,96,102,108,112,119,127,141,159,165,191,195],"task":[3],"of":[4,38,98,115,129,167],"customized":[5],"image":[6,24,61,100,211],"editing":[7,212],"using":[8,213],"a":[9,22,28,32,56,74,78,123,130,136,153,172,184,217],"text-conditioned":[10],"Diffusion":[11],"Model":[12],"(DM).":[13],"The":[14],"goal":[15],"is":[16],"to":[17,62,76],"fuse":[18],"subject":[20,161,199],"in":[21,111,118,200],"reference":[23,160,198],"(e.g.,":[25,31,41,149],"sunglasses)":[26],"with":[27],"source":[29,142,196],"one":[30,99],"boy),":[33],"while":[34],"retaining":[35],"fidelity":[37,97,166,202],"them":[39],"both":[40],"boy":[43],"wearing":[44],"sunglasses).":[46],"An":[47],"intuitive":[48],"approach,":[49],"called":[50],"LoRA":[51,58,138,162,186],"fusion,":[52],"first":[53],"separately":[54],"trains":[55],"DM":[57],"for":[59,140],"each":[60],"encode":[63],"its":[64,146,168],"details.":[65],"Then":[66,207],"two":[68],"LoRAs":[69],"are":[70],"linearly":[71],"combined":[72],"by":[73],"weight":[75,139,188,215],"generate":[77],"fused":[79],"image.":[80],"Unfortunately,":[81],"even":[82],"through":[83],"careful":[84],"grid":[85],"search":[86],"or":[87],"learning":[88],"weight,":[90],"this":[91,177,214],"approach":[92],"still":[93],"trades":[94],"off":[95],"against":[101],"other.":[103],"point":[105],"out":[106],"that":[107,189],"evil":[109],"lies":[110],"overlooked":[113],"role":[114],"diffusion":[116],"time-step":[117,125],"generation":[120,128],"process,":[121],"i.e.,":[122,193],"smaller":[124],"controls":[126],"more":[131],"fine-grained":[132,147],"attribute.":[133],"For":[134],"example,":[135],"large":[137],"may":[143],"help":[144],"preserve":[145],"details":[148],"face":[150],"attributes)":[151],"at":[152,171],"small":[154],"time-step,":[155],"but":[156],"could":[157],"overpower":[158],"and":[163,197,216],"lose":[164],"overall":[169],"shape":[170],"larger":[173],"time-step.":[174],"To":[175],"address":[176],"deficiency,":[178],"we":[179,208],"propose":[180],"TimeFusion,":[181],"which":[182],"learns":[183],"time-step-specific":[185],"fusion":[187],"resolves":[190],"trade-off,":[192],"generating":[194],"high":[201],"given":[203],"their":[204],"respective":[205],"prompt.":[206,219],"can":[209],"customize":[210],"target":[218]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}