{"id":"https://openalex.org/W4414360070","doi":"https://doi.org/10.24963/ijcai.2025/106","title":"Unleashing the Semantic Adaptability of Controlled Diffusion Model for Image Colorization","display_name":"Unleashing the Semantic Adaptability of Controlled Diffusion Model for Image Colorization","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360070","doi":"https://doi.org/10.24963/ijcai.2025/106"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/106","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047942518","display_name":"Xiangcheng Du","orcid":"https://orcid.org/0000-0002-4268-6114"},"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":"Xiangcheng Du","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665357","display_name":"Zhao Zhou","orcid":"https://orcid.org/0000-0001-7069-6275"},"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":"Zhao Zhou","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113362809","display_name":"Yanlong Wang","orcid":"https://orcid.org/0009-0009-3710-4886"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlong Wang","raw_affiliation_strings":["Shanxi University, Taiyuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056833841","display_name":"Yingbin Zheng","orcid":"https://orcid.org/0000-0002-5590-9292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingbin Zheng","raw_affiliation_strings":["Videt Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Videt Lab, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043728985","display_name":"Xingjiao Wu","orcid":"https://orcid.org/0000-0001-9146-051X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjiao Wu","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002186127","display_name":"Peizhu Gong","orcid":"https://orcid.org/0000-0002-9556-089X"},"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":"Peizhu Gong","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100625873","display_name":"Cheng Jin","orcid":"https://orcid.org/0000-0003-3063-1957"},"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":"Cheng Jin","raw_affiliation_strings":["Fudan University, Shanghai, China","Innovation Center of Calligraphy and Painting Creation Technology, MCT, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Innovation Center of Calligraphy and Painting Creation Technology, MCT, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"945","last_page":"953"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11666","display_name":"Color Science and Applications","score":0.8906000256538391,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11666","display_name":"Color Science and Applications","score":0.8906000256538391,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7621999979019165,"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/grayscale","display_name":"Grayscale","score":0.6815999746322632},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6087999939918518},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5156999826431274},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4302999973297119},{"id":"https://openalex.org/keywords/color-image","display_name":"Color image","score":0.3880999982357025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3758000135421753},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.3483999967575073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390000224113464},{"id":"https://openalex.org/C78201319","wikidata":"https://www.wikidata.org/wiki/Q685727","display_name":"Grayscale","level":3,"score":0.6815999746322632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6711999773979187},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6087999939918518},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4302999973297119},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41260001063346863},{"id":"https://openalex.org/C142616399","wikidata":"https://www.wikidata.org/wiki/Q5148604","display_name":"Color image","level":4,"score":0.3880999982357025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2778307483","wikidata":"https://www.wikidata.org/wiki/Q5149038","display_name":"Colored","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2912999987602234},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/106","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Recent":[0],"data-driven":[1],"image":[2,49,137],"colorization":[3],"methods":[4],"have":[5],"leveraged":[6],"pre-trained":[7],"Text-to-Image":[8],"(T2I)":[9],"diffusion":[10,66,87],"models":[11],"as":[12],"generative":[13],"prior,":[14],"while":[15,40,85],"still":[16],"suffering":[17],"from":[18,80],"unsatisfactory":[19],"and":[20,47,62,93,99,113],"inaccurate":[21],"semantic-level":[22],"color":[23,46,83],"control.":[24],"To":[25],"address":[26],"these":[27],"issues,":[28],"we":[29],"propose":[30],"a":[31,54,63,105],"Semantic":[32],"Adaptation":[33],"method":[34,128],"(SeAda)":[35],"that":[36,126],"enhances":[37],"the":[38,42,74,78,86,90],"prior":[39,94,114],"considering":[41],"semantic":[43,55,60,75,111],"discrepancy":[44],"between":[45],"grayscale":[48,81],"pairs.":[50],"The":[51],"SeAda":[52],"employs":[53],"adapter":[56,76],"to":[57,68,82,96,109],"produce":[58],"refined":[59,91],"embeddings":[61],"controlled":[64],"T2I":[65],"model":[67,88],"create":[69],"reasonably":[70],"colored":[71],"images.":[72],"Specifically,":[73],"transfers":[77],"embedding":[79,92],"domain,":[84],"utilizes":[89],"knowledge":[95],"achieve":[97],"realistic":[98],"diverse":[100],"results.":[101],"We":[102],"also":[103],"design":[104],"three-staged":[106],"training":[107],"strategy":[108],"improve":[110],"comprehension":[112],"integration":[115],"for":[116],"further":[117],"performance":[118,135],"improvement.":[119],"Extensive":[120],"experiments":[121],"on":[122],"public":[123],"datasets":[124],"demonstrate":[125],"our":[127],"outperforms":[129],"existing":[130],"state-of-the-art":[131],"techniques,":[132],"yielding":[133],"superior":[134],"in":[136],"colorization.":[138]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}