{"id":"https://openalex.org/W4416169543","doi":"https://doi.org/10.1109/iccv51701.2025.01549","title":"CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation","display_name":"CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416169543","doi":"https://doi.org/10.1109/iccv51701.2025.01549"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01549","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/2509.01028","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103537656","display_name":"Zixin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zixin Zhu","raw_affiliation_strings":["University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099042086","display_name":"Kevin Duarte","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Duarte","raw_affiliation_strings":["Adobe Inc. (ASML)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Inc. (ASML)","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079190639","display_name":"Mamshad Nayeem Rizve","orcid":"https://orcid.org/0000-0001-5378-1697"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mamshad Nayeem Rizve","raw_affiliation_strings":["Adobe Inc. (ASML)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Inc. (ASML)","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028194519","display_name":"Chengyuan Xu","orcid":"https://orcid.org/0000-0001-9981-8889"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengyuan Xu","raw_affiliation_strings":["Adobe Inc. (ASML)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Inc. (ASML)","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113715195","display_name":"Ratheesh Kalarot","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ratheesh Kalarot","raw_affiliation_strings":["Adobe Inc. (ASML)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Inc. (ASML)","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085245110","display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7324-7034"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38286006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16682","last_page":"16691"},"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":0.9728000164031982,"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":0.9728000164031982,"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":0.004600000102072954,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.003800000064074993,"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/variety","display_name":"Variety (cybernetics)","score":0.6039000153541565},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.5828999876976013},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5792999863624573},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4862000048160553},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4050999879837036},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.33649998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6123999953269958},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5792999863624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4878999888896942},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3625999987125397},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01549","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:2509.01028","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.01028","pdf_url":"https://arxiv.org/pdf/2509.01028","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2509.01028","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.01028","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.01028","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.01028","pdf_url":"https://arxiv.org/pdf/2509.01028","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"text-to-image":[1],"(T2I)":[2],"generation,":[3],"achieving":[4],"fine-grained":[5],"control":[6,30,60,100],"over":[7],"attributes":[8,63,74,102,162],"-":[9,15],"such":[10],"as":[11],"age":[12],"or":[13],"smile":[14],"remains":[16],"challenging,":[17],"even":[18],"with":[19],"detailed":[20],"text":[21],"prompts.":[22],"Slider-based":[23],"methods":[24],"offer":[25],"a":[26,51,91,158],"solution":[27],"for":[28,40,94,148],"precise":[29,59],"of":[31,61,131,160],"image":[32,161],"attributes.":[33,49],"Existing":[34],"approaches":[35],"typically":[36],"train":[37],"individual":[38],"adapter":[39],"each":[41],"attribute":[42,84,115],"separately,":[43],"overlooking":[44],"the":[45,95,122,128,132,140,145],"entanglement":[46],"among":[47,55],"multiple":[48,62,73,101,114],"As":[50],"result,":[52],"interference":[53],"occurs":[54],"different":[56],"attributes,":[57],"preventing":[58],"together.":[64],"To":[65],"address":[66],"this":[67],"challenge,":[68],"we":[69,105],"aim":[70],"to":[71,78,99,112,169],"disentangle":[72],"in":[75,127],"slider-based":[76],"generation":[77],"enbale":[79],"more":[80],"reliable":[81],"and":[82,109,135,151,163],"independent":[83],"manipulation.":[85],"Our":[86],"approach,":[87],"CompSlider,":[88],"can":[89],"generate":[90],"conditional":[92,133],"prior":[93,134],"T2I":[96],"foundation":[97,141],"model":[98],"simultaneously.":[103],"Furthermore,":[104],"introduce":[106],"novel":[107],"disentanglement":[108],"structure":[110],"losses":[111],"compose":[113],"changes":[116],"while":[117],"maintaining":[118],"structural":[119],"consistency":[120],"within":[121],"image.":[123],"Since":[124],"CompSlider":[125],"operates":[126],"latent":[129],"space":[130],"does":[136],"not":[137],"require":[138],"retraining":[139],"model,":[142],"it":[143],"reduces":[144],"computational":[146],"burden":[147],"both":[149],"training":[150],"inference.":[152],"We":[153],"evaluate":[154],"our":[155],"approach":[156],"on":[157],"variety":[159],"highlight":[164],"its":[165],"generality":[166],"by":[167],"extending":[168],"video":[170],"generation.":[171]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}