{"id":"https://openalex.org/W4392151693","doi":"https://doi.org/10.1109/tcsvt.2024.3369757","title":"DisenDreamer: Subject-Driven Text-to-Image Generation With Sample-Aware Disentangled Tuning","display_name":"DisenDreamer: Subject-Driven Text-to-Image Generation With Sample-Aware Disentangled Tuning","publication_year":2024,"publication_date":"2024-02-26","ids":{"openalex":"https://openalex.org/W4392151693","doi":"https://doi.org/10.1109/tcsvt.2024.3369757"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3369757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3369757","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5100420416","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-0943-2286"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hong Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088844431","display_name":"Y. J. Zhang","orcid":"https://orcid.org/0009-0002-0886-8296"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yipeng Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Beijing National Research Center for Information Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, China","institution_ids":["https://openalex.org/I4210156423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028258340","display_name":"Xuguang Duan","orcid":"https://orcid.org/0000-0001-9108-9618"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Duan","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101273536","display_name":"Yuwei Zhou","orcid":"https://orcid.org/0000-0001-9582-7331"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Zhou","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Beijing National Research Center for Information Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, China","institution_ids":["https://openalex.org/I4210156423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100420416"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":9.7369,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.98771829,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"34","issue":"8","first_page":"6860","last_page":"6873"},"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":0.9994999766349792,"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":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.994700014591217,"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":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6763041019439697},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5334029197692871},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4451879560947418},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4319559931755066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4105713963508606},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36662739515304565},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15407082438468933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6763041019439697},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5334029197692871},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4451879560947418},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4319559931755066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4105713963508606},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36662739515304565},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15407082438468933},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3369757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3369757","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G119957897","display_name":null,"funder_award_id":"62102222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1527691513","display_name":null,"funder_award_id":"62250008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1622659961","display_name":null,"funder_award_id":"2023YFF1205001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1950392669","display_name":null,"funder_award_id":"BNR2023RC01003","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G3022012397","display_name":null,"funder_award_id":"BNR2023TD03006","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G8567821897","display_name":null,"funder_award_id":"62222209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2163922914","https://openalex.org/W2771558241","https://openalex.org/W2962785568","https://openalex.org/W2962917899","https://openalex.org/W2963966654","https://openalex.org/W3035316078","https://openalex.org/W3169346140","https://openalex.org/W3215495615","https://openalex.org/W3216352822","https://openalex.org/W4224035735","https://openalex.org/W4287029626","https://openalex.org/W4289785095","https://openalex.org/W4309802554","https://openalex.org/W4309805490","https://openalex.org/W4312740349","https://openalex.org/W4312872987","https://openalex.org/W4312933868","https://openalex.org/W4313484371","https://openalex.org/W4318624501","https://openalex.org/W4327842770","https://openalex.org/W4362598082","https://openalex.org/W4384264739","https://openalex.org/W4385271055","https://openalex.org/W4386057725","https://openalex.org/W4386071814","https://openalex.org/W4386072096","https://openalex.org/W4386075639","https://openalex.org/W4386076215","https://openalex.org/W4386076425","https://openalex.org/W4390871953","https://openalex.org/W4390872341","https://openalex.org/W4390872387","https://openalex.org/W4390873054","https://openalex.org/W4390874393","https://openalex.org/W4402753775","https://openalex.org/W6751772990","https://openalex.org/W6756663807","https://openalex.org/W6757817989","https://openalex.org/W6767551140","https://openalex.org/W6778883912","https://openalex.org/W6779068807","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6803924141","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6840155194","https://openalex.org/W6841366371","https://openalex.org/W6841755765","https://openalex.org/W6846186717","https://openalex.org/W6846687901","https://openalex.org/W6847131820","https://openalex.org/W6847548068","https://openalex.org/W6847587260","https://openalex.org/W6849367332","https://openalex.org/W6851190826","https://openalex.org/W6851513319","https://openalex.org/W6852060089","https://openalex.org/W6854299454"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Subject-driven":[0],"text-to-image":[1,92,177],"generation":[2,93,191],"aims":[3],"to":[4,27,69,117,126,136],"generate":[5],"customized":[6],"images":[7],"of":[8,51],"the":[9,14,34,38,41,46,49,52,57,62,80,100,105,128,138,143,149,158,182,185],"given":[10],"subject":[11,71],"based":[12],"on":[13],"text":[15,75,124],"descriptions,":[16],"which":[17],"has":[18],"drawn":[19],"increasing":[20],"attention":[21],"recently.":[22],"Existing":[23],"methods":[24],"mainly":[25],"resort":[26],"finetuning":[28],"a":[29,85,122,132],"pretrained":[30,101],"generative":[31],"model,":[32],"where":[33],"identity-relevant":[35,129,183],"information":[36,44,130],"(e.g.,":[37,45],"boy)":[39,53],"and":[40,74,131,157,184,193],"identity-irrelevant":[42,139,186],"sample-specific":[43,133],"background":[47],"or":[48],"pose":[50],"are":[54],"entangled":[55,64,115],"in":[56,94,104],"latent":[58,65],"embedding":[59,66,116,125,135,160],"space.":[60],"However,":[61],"highly":[63],"may":[67],"lead":[68],"low":[70],"identity":[72],"fidelity":[73],"prompt":[76],"fidelity.":[77],"To":[78,141],"tackle":[79],"problems,":[81],"we":[82,146],"propose":[83],"DisenDreamer,":[84],"sample-aware":[86,155],"disentangled":[87],"tuning":[88,162],"framework":[89,171],"for":[90,175],"subject-driven":[91,176],"this":[95],"paper.":[96],"Specifically,":[97],"DisenDreamer":[98,119,170,188],"finetunes":[99],"diffusion":[102],"model":[103],"denoising":[106],"process.":[107],"Different":[108],"from":[109],"previous":[110],"works":[111],"that":[112,167],"utilize":[113],"an":[114],"denoise,":[118],"instead":[120],"utilizes":[121],"common":[123,152],"capture":[127,137],"visual":[134],"information.":[140],"disentangle":[142],"two":[144],"embeddings,":[145],"further":[147],"design":[148],"novel":[150],"weak":[151,154],"denoising,":[153,156],"contrastive":[159],"auxiliary":[161],"objectives.":[163],"Extensive":[164],"experiments":[165],"show":[166],"our":[168],"proposed":[169],"outperforms":[172],"baseline":[173],"models":[174],"generation.":[178],"Additionally,":[179],"by":[180],"combining":[181],"embedding,":[187],"demonstrates":[189],"more":[190],"flexibility":[192],"controllability.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}