{"id":"https://openalex.org/W4415536485","doi":"https://doi.org/10.1145/3746027.3755524","title":"AnimeColor: Reference-based Animation Colorization with Diffusion Transformers","display_name":"AnimeColor: Reference-based Animation Colorization with Diffusion Transformers","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536485","doi":"https://doi.org/10.1145/3746027.3755524"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5004323368","display_name":"Yuhong Zhang","orcid":"https://orcid.org/0009-0000-8902-0013"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhong Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-8902-0013","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011748710","display_name":"L.X. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyao Wang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0001-2670-5397","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111215638","display_name":"H J Wang","orcid":"https://orcid.org/0009-0008-0995-0092"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-0995-0092","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110390524","display_name":"D. P. Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danni Wu","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-3954-590X","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064575558","display_name":"Zuzeng Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuzeng Lin","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0000-1281-6814","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100615165","display_name":"Wang Feng","orcid":"https://orcid.org/0000-0002-7669-2547"},"institutions":[{"id":"https://openalex.org/I4210146168","display_name":"CREATe Centre","ror":"https://ror.org/04e30s833","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210146168"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Feng Wang","raw_affiliation_strings":["CreateAI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7669-2547","affiliations":[{"raw_affiliation_string":"CreateAI, Beijing, China","institution_ids":["https://openalex.org/I4210146168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002404808","display_name":"Li Song","orcid":"https://orcid.org/0000-0002-7124-5182"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Song","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7124-5182","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6682","last_page":"6690"},"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":0.9952999949455261,"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":0.9952999949455261,"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/T12290","display_name":"Human Motion and Animation","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9865999817848206,"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/animation","display_name":"Animation","score":0.7924000024795532},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6223999857902527},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.41200000047683716},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.35429999232292175},{"id":"https://openalex.org/keywords/color-coding","display_name":"Color-coding","score":0.33550000190734863},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3327000141143799},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.29100000858306885},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2815999984741211}],"concepts":[{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7924000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900000214576721},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6845999956130981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6790000200271606},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6223999857902527},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5303999781608582},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C104597421","wikidata":"https://www.wikidata.org/wiki/Q5148529","display_name":"Color-coding","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C173752661","wikidata":"https://www.wikidata.org/wiki/Q1396414","display_name":"Color quantization","level":5,"score":0.2700999975204468},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C142616399","wikidata":"https://www.wikidata.org/wiki/Q5148604","display_name":"Color image","level":4,"score":0.26750001311302185},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.26339998841285706},{"id":"https://openalex.org/C60851780","wikidata":"https://www.wikidata.org/wiki/Q17056736","display_name":"Interactive skeleton-driven simulation","level":5,"score":0.25929999351501465},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W69951162","https://openalex.org/W2902318149","https://openalex.org/W2978052557","https://openalex.org/W3042885582","https://openalex.org/W3193744354","https://openalex.org/W4312353784","https://openalex.org/W4312933868","https://openalex.org/W4361287588","https://openalex.org/W4390873054","https://openalex.org/W4390874575","https://openalex.org/W4392103189","https://openalex.org/W4403748157","https://openalex.org/W4404525440"],"related_works":[],"abstract_inverted_index":{"Animation":[0],"colorization":[1,31,137],"plays":[2],"a":[3,27,43,57,68,94,141],"vital":[4],"role":[5],"in":[6,115,135],"animation":[7,30,50,136],"production,":[8],"yet":[9],"existing":[10,113],"methods":[11,114],"struggle":[12],"to":[13,62,73,85,98],"achieve":[14],"color":[15,65,76,105,116],"accuracy":[16],"and":[17,67,122],"temporal":[18,120],"consistency.":[19],"To":[20],"address":[21],"these":[22],"challenges,":[23],"we":[24,92],"propose":[25],"AnimeColor,":[26],"novel":[28],"reference-based":[29],"framework":[32,126],"leveraging":[33],"Diffusion":[34],"Transformers":[35],"(DiT).":[36],"Our":[37,125],"approach":[38],"integrates":[39],"sketch":[40,118],"sequences":[41],"into":[42],"DiT-based":[44],"video":[45,88],"diffusion":[46,89],"model,":[47],"enabling":[48],"sketch-controlled":[49],"generation.":[51],"We":[52],"introduce":[53],"two":[54],"key":[55],"components:":[56],"High-level":[58],"Color":[59,70],"Extractor":[60],"(HCE)":[61],"capture":[63],"semantic":[64],"information":[66],"Low-level":[69],"Guider":[71],"(LCG)":[72],"extract":[74],"fine-grained":[75],"details":[77],"from":[78],"reference":[79,103],"images.":[80],"These":[81],"components":[82],"work":[83],"synergistically":[84],"guide":[86],"the":[87,100,130,133],"process.":[90],"Additionally,":[91],"employ":[93],"multi-stage":[95],"training":[96],"strategy":[97],"maximize":[99],"utilization":[101],"of":[102,132],"image":[104],"information.":[106],"Extensive":[107],"experiments":[108],"demonstrate":[109],"that":[110],"AnimeColor":[111],"outperforms":[112],"accuracy,":[117],"alignment,":[119],"consistency,":[121],"visual":[123],"quality.":[124],"not":[127],"only":[128],"advances":[129],"state":[131],"art":[134],"but":[138],"also":[139],"provides":[140],"practical":[142],"solution":[143],"for":[144],"industrial":[145],"applications.":[146],"The":[147],"code":[148],"will":[149],"be":[150],"made":[151],"publicly":[152],"available":[153],"at":[154],"https://github.com/IamCreateAI/AnimeColor.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
