{"id":"https://openalex.org/W7113897817","doi":"https://doi.org/10.1145/3757376.3771391","title":"ChromaFlow: End-to-End Flow Matching for Efficient Video Colorization","display_name":"ChromaFlow: End-to-End Flow Matching for Efficient Video Colorization","publication_year":2025,"publication_date":"2025-12-10","ids":{"openalex":"https://openalex.org/W7113897817","doi":"https://doi.org/10.1145/3757376.3771391"},"language":null,"primary_location":{"id":"doi:10.1145/3757376.3771391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757376.3771391","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Technical Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3757376.3771391","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hanyuan Liu","orcid":"https://orcid.org/0009-0003-3336-0686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanyuan Liu","raw_affiliation_strings":["Saint Francis University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0003-3336-0686","affiliations":[{"raw_affiliation_string":"Saint Francis University, Hong Kong, Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chengze Li","orcid":"https://orcid.org/0000-0002-1519-750X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengze Li","raw_affiliation_strings":["Saint Francis University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-1519-750X","affiliations":[{"raw_affiliation_string":"Saint Francis University, Hong Kong, Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tien-Tsin Wong","orcid":"https://orcid.org/0000-0002-7792-9307"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tien-Tsin Wong","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7792-9307","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xueting Liu","orcid":"https://orcid.org/0000-0002-0868-5353"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueting Liu","raw_affiliation_strings":["Saint Francis University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-0868-5353","affiliations":[{"raw_affiliation_string":"Saint Francis University, Hong Kong, Hong Kong","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9291999936103821,"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":0.9291999936103821,"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":0.0203000009059906,"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":0.005400000140070915,"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/chrominance","display_name":"Chrominance","score":0.8727999925613403},{"id":"https://openalex.org/keywords/color-space","display_name":"Color space","score":0.392300009727478},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3813000023365021},{"id":"https://openalex.org/keywords/compression-artifact","display_name":"Compression artifact","score":0.37790000438690186},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.3456000089645386},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.33180001378059387},{"id":"https://openalex.org/keywords/luminance","display_name":"Luminance","score":0.3176000118255615},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3172999918460846}],"concepts":[{"id":"https://openalex.org/C163204269","wikidata":"https://www.wikidata.org/wiki/Q355263","display_name":"Chrominance","level":3,"score":0.8727999925613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789999842643738},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6495000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6438999772071838},{"id":"https://openalex.org/C2961294","wikidata":"https://www.wikidata.org/wiki/Q166863","display_name":"Color space","level":3,"score":0.392300009727478},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.37790000438690186},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C73313986","wikidata":"https://www.wikidata.org/wiki/Q355386","display_name":"Luminance","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C2779407163","wikidata":"https://www.wikidata.org/wiki/Q1189998","display_name":"YCbCr","level":5,"score":0.30309998989105225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757376.3771391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757376.3771391","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Technical Communications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3757376.3771391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757376.3771391","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Technical Communications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6395541429519653,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G346266166","display_name":null,"funder_award_id":"UGC/FDS11/E02/23","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"}],"funders":[{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2768814045","https://openalex.org/W2957365494","https://openalex.org/W2979841973","https://openalex.org/W2989277455","https://openalex.org/W4246399762","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4385453640","https://openalex.org/W4386598488","https://openalex.org/W4390874124","https://openalex.org/W4415798523"],"related_works":[],"abstract_inverted_index":{"Video":[0],"colorization":[1,31,44,50,89],"remains":[2],"challenging":[3],"to":[4,47,133],"produce":[5],"vivid":[6],"and":[7,76,99,110,130,143],"semantically":[8],"appropriate":[9],"colors":[10],"with":[11,88,96],"temporal":[12,128],"consistency.":[13],"Existing":[14],"diffusion":[15],"approaches":[16],"typically":[17],"learn":[18],"in":[19,68,125],"an":[20],"RGB-based":[21],"latent":[22,65],"space,":[23],"which":[24],"bridge":[25],"a":[26,39,63,93],"domain":[27],"mismatch":[28],"for":[29,42],"downstream":[30],"applications.":[32],"In":[33],"this":[34],"work,":[35],"we":[36],"present":[37],"ChromaFlow,":[38],"novel":[40],"framework":[41],"video":[43,108],"that":[45,72,120],"adheres":[46],"the":[48,69],"fundamental":[49],"formulation:":[51],"directly":[52],"predicting":[53],"chrominance":[54],"components":[55],"conditioned":[56],"on":[57],"luminance.":[58],"Our":[59],"key":[60],"innovation":[61],"is":[62],"DCT-based":[64],"compression":[66],"mechanism":[67],"YCbCr":[70],"space":[71],"naturally":[73],"decouples":[74],"luma":[75],"chroma":[77],"components,":[78],"significantly":[79],"reducing":[80],"computational":[81],"cost":[82],"while":[83,136],"maintaining":[84],"perceptual":[85],"quality":[86],"aligned":[87],"objectives.":[90],"ChromaFlow":[91,121],"employs":[92],"Diffusion":[94],"Transformer":[95],"linear":[97],"attention":[98],"asynchronous":[100],"flow":[101],"matching,":[102],"enabling":[103],"efficient":[104],"processing":[105],"of":[106],"long":[107],"sequences":[109],"natural":[111],"color":[112,126],"propagation":[113],"from":[114],"reference":[115,144],"frames.":[116,145],"Extensive":[117],"experiments":[118],"demonstrate":[119],"achieves":[122],"superior":[123],"performance":[124],"accuracy,":[127],"coherence,":[129],"controllability":[131],"compared":[132],"state-of-the-art":[134],"methods,":[135],"supporting":[137],"conditioning":[138],"modalities":[139],"including":[140],"text":[141],"prompts":[142],"Project":[146],"page:":[147],"https://chroma-flow.github.io.":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-11T00:00:00"}