{"id":"https://openalex.org/W4416033243","doi":"https://doi.org/10.1109/wacv61042.2026.00742","title":"Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models","display_name":"Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416033243","doi":"https://doi.org/10.1109/wacv61042.2026.00742"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/2503.09864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062781240","display_name":"H\u00e9ctor Laria","orcid":null},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"H\u00e9ctor Laria","raw_affiliation_strings":["Computer Vision Center,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119833538","display_name":"Alexandra Gomez-Villa","orcid":null},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alexandra Gomez-Villa","raw_affiliation_strings":["Computer Vision Center,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011078617","display_name":"Jiang Qin","orcid":"https://orcid.org/0000-0002-6949-6556"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Qin","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064713301","display_name":"Muhammad Atif Butt","orcid":"https://orcid.org/0000-0002-4799-6488"},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Muhammad Atif Butt","raw_affiliation_strings":["Computer Vision Center,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088254508","display_name":"Bogdan Raducanu","orcid":"https://orcid.org/0000-0003-2207-6260"},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Bogdan Raducanu","raw_affiliation_strings":["Computer Vision Center,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033437430","display_name":"Javier Vazquez-Corral","orcid":null},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Vazquez-Corral","raw_affiliation_strings":["Computer Vision Center,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105984500","display_name":"Joost van de Weijer","orcid":"https://orcid.org/0000-0001-9843-3143"},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joost van de Weijer","raw_affiliation_strings":["Computer Vision Center,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100437002","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-2937-9339"},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Computer Vision Center,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center,Spain","institution_ids":["https://openalex.org/I4387153096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":null,"issue":null,"first_page":"7689","last_page":"7698"},"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":0.7021999955177307,"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":0.7021999955177307,"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/T11019","display_name":"Image Enhancement Techniques","score":0.03370000049471855,"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/T12496","display_name":"Color perception and design","score":0.026599999517202377,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6769000291824341},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6082000136375427},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5669000148773193},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.498199999332428},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44429999589920044},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4352000057697296},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4092999994754791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065999746322632},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6769000291824341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6496999859809875},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.498199999332428},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4244999885559082},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C142616399","wikidata":"https://www.wikidata.org/wiki/Q5148604","display_name":"Color image","level":4,"score":0.32429999113082886},{"id":"https://openalex.org/C36262787","wikidata":"https://www.wikidata.org/wiki/Q2294018","display_name":"Color model","level":4,"score":0.3158999979496002},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.09864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.09864","pdf_url":"https://arxiv.org/pdf/2503.09864","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.2503.09864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.09864","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":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:2503.09864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.09864","pdf_url":"https://arxiv.org/pdf/2503.09864","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":{"Recent":[0],"advances":[1],"in":[2,37,57,114],"text-to-image":[3],"(T2I)":[4],"diffusion":[5,58],"models":[6,59],"have":[7],"enabled":[8],"remarkable":[9],"control":[10,56],"over":[11],"various":[12],"attributes,":[13],"yet":[14],"precise":[15,93],"color":[16,55,77,94],"specification":[17],"remains":[18],"a":[19,47,130],"fundamental":[20],"challenge.":[21],"Existing":[22],"approaches,":[23],"such":[24],"as":[25],"ColorPeel,":[26],"rely":[27],"on":[28],"model":[29],"personalization,":[30],"requiring":[31],"additional":[32],"optimization":[33],"and":[34,79,109,116],"limiting":[35],"flexibility":[36],"specifying":[38],"arbitrary":[39],"colors.":[40],"In":[41],"this":[42,84],"work,":[43],"we":[44,70,125],"introduce":[45],"ColorWave,":[46],"novel":[48],"training-free":[49],"approach":[50,105],"that":[51,127],"achieves":[52],"exact":[53],"RGB-level":[54],"without":[60],"fine-tuning.":[61],"By":[62],"systematically":[63],"analyzing":[64],"the":[65,98],"cross-attention":[66],"mechanisms":[67],"within":[68],"IP-Adapter,":[69],"uncover":[71],"an":[72],"implicit":[73],"binding":[74],"between":[75],"textual":[76],"descriptors":[78],"reference":[80],"image":[81,137],"features.":[82],"Leveraging":[83],"insight,":[85],"our":[86],"method":[87],"rewires":[88],"these":[89],"bindings":[90],"to":[91],"enforce":[92],"attribution":[95],"while":[96],"preserving":[97],"generative":[99],"capabilities":[100],"of":[101],"pretrained":[102],"models.":[103],"Our":[104],"maintains":[106],"generation":[107],"quality":[108],"diversity,":[110],"outperforming":[111],"prior":[112],"methods":[113],"accuracy":[115],"applicability":[117],"across":[118],"diverse":[119],"object":[120],"categories.":[121],"Through":[122],"extensive":[123],"evaluations,":[124],"demonstrate":[126],"ColorWave":[128],"establishes":[129],"new":[131],"paradigm":[132],"for":[133],"structured,":[134],"color-consistent":[135],"diffusion-based":[136],"synthesis.":[138]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
