{"id":"https://openalex.org/W4410737556","doi":"https://doi.org/10.1109/tcsvt.2025.3573401","title":"Leveraging the Powerful Attention of a Pre-Trained Diffusion Model for Exemplar-Based Image Colorization","display_name":"Leveraging the Powerful Attention of a Pre-Trained Diffusion Model for Exemplar-Based Image Colorization","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4410737556","doi":"https://doi.org/10.1109/tcsvt.2025.3573401"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3573401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3573401","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15812","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010134544","display_name":"Satoshi Kosugi","orcid":"https://orcid.org/0000-0001-7556-9072"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Satoshi Kosugi","raw_affiliation_strings":["Institute of Integrated Research, Institute of Science Tokyo, Yokohama, Kanagawa, Japan","Institute of Integrated Research, Institute of Science Tokyo, Yokohama, Kanagawa"],"raw_orcid":"https://orcid.org/0000-0001-7556-9072","affiliations":[{"raw_affiliation_string":"Institute of Integrated Research, Institute of Science Tokyo, Yokohama, Kanagawa, Japan","institution_ids":[]},{"raw_affiliation_string":"Institute of Integrated Research, Institute of Science Tokyo, Yokohama, Kanagawa","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010134544"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1473,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91682791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"10","first_page":"10059","last_page":"10069"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9955999851226807,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9914000034332275,"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/computer-science","display_name":"Computer science","score":0.6845359206199646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6355741620063782},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5309241414070129},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5295088291168213},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4714090824127197},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.44471126794815063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4267708659172058},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.415485143661499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845359206199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6355741620063782},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5309241414070129},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5295088291168213},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4714090824127197},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.44471126794815063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4267708659172058},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.415485143661499},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3573401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3573401","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2505.15812","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15812","pdf_url":"https://arxiv.org/pdf/2505.15812","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15812","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15812","pdf_url":"https://arxiv.org/pdf/2505.15812","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410737556.pdf","grobid_xml":"https://content.openalex.org/works/W4410737556.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1566135517","https://openalex.org/W1677409904","https://openalex.org/W1686810756","https://openalex.org/W1694135408","https://openalex.org/W1901129140","https://openalex.org/W1975030698","https://openalex.org/W1986416281","https://openalex.org/W2104853049","https://openalex.org/W2108598243","https://openalex.org/W2124386111","https://openalex.org/W2161969291","https://openalex.org/W2809852002","https://openalex.org/W2929832686","https://openalex.org/W2931764303","https://openalex.org/W2962785568","https://openalex.org/W2963073614","https://openalex.org/W2963350227","https://openalex.org/W2982041717","https://openalex.org/W2998723654","https://openalex.org/W3000407986","https://openalex.org/W3034583007","https://openalex.org/W3035595647","https://openalex.org/W3035712445","https://openalex.org/W3093418165","https://openalex.org/W3121370741","https://openalex.org/W3162681312","https://openalex.org/W3166326887","https://openalex.org/W3207381926","https://openalex.org/W3207692456","https://openalex.org/W3214212133","https://openalex.org/W4214745154","https://openalex.org/W4221161505","https://openalex.org/W4226227850","https://openalex.org/W4235795445","https://openalex.org/W4247941455","https://openalex.org/W4248617091","https://openalex.org/W4285240117","https://openalex.org/W4289785045","https://openalex.org/W4303683350","https://openalex.org/W4311802540","https://openalex.org/W4311806086","https://openalex.org/W4312933868","https://openalex.org/W4313590718","https://openalex.org/W4380451230","https://openalex.org/W4384151580","https://openalex.org/W4386113271","https://openalex.org/W4387042228","https://openalex.org/W4390204279","https://openalex.org/W4390873195","https://openalex.org/W4390873774","https://openalex.org/W4390899072","https://openalex.org/W4394625665","https://openalex.org/W4396782819","https://openalex.org/W4402667886","https://openalex.org/W4402775818","https://openalex.org/W4403012171","https://openalex.org/W4403757510","https://openalex.org/W4413273196"],"related_works":["https://openalex.org/W2386796262","https://openalex.org/W3177740930","https://openalex.org/W1484549928","https://openalex.org/W1974805659","https://openalex.org/W2811388477","https://openalex.org/W2011653655","https://openalex.org/W1982781720","https://openalex.org/W4281941122","https://openalex.org/W2027328791","https://openalex.org/W2390836331"],"abstract_inverted_index":{"Exemplar-based":[0],"image":[1,8,111,199],"colorization":[2,166],"aims":[3],"to":[4,20,90,115,146,203,228],"colorize":[5],"a":[6,10,42,50,64,70],"grayscale":[7,132,153],"using":[9],"reference":[11,16,99,110],"color":[12,83,106,139,155],"image,":[13,123],"ensuring":[14],"that":[15,190],"colors":[17,172],"are":[18,134],"applied":[19],"corresponding":[21,138],"input":[22,97,122],"regions":[23,119],"based":[24,68],"on":[25,49,69,235],"their":[26],"semantic":[27,32,103,160],"similarity.":[28],"To":[29,58],"achieve":[30],"accurate":[31],"matching":[33,118],"between":[34,95],"regions,":[35],"we":[36,62,79,142,163,207,233],"leverage":[37],"the":[38,87,96,109,116,121,131,137,152,170,182,204,229],"self-attention":[39,88],"module":[40,89],"of":[41,120,184,198,218,225,241,244,253,258],"pre-trained":[43,71],"diffusion":[44,72],"model,":[45,73],"which":[46,168,239],"is":[47,112,263],"trained":[48],"large":[51],"dataset":[52],"and":[53,98,129,154,176,201,222,247,255],"exhibits":[54],"powerful":[55],"attention":[56,93,127,145,148],"capabilities.":[57],"harness":[59],"this":[60,126],"power,":[61],"propose":[63,164],"novel,":[65],"fine-tuning-free":[66],"approach":[67],"making":[74],"two":[75],"key":[76],"contributions.":[77],"First,":[78],"introduce":[80],"dual":[81,144],"attention-guided":[82],"transfer.":[84],"We":[85],"utilize":[86,143],"compute":[91],"an":[92,216,223,251,256],"map":[94],"images,":[100,156],"effectively":[101],"capturing":[102],"correspondences.":[104],"The":[105],"features":[107,133],"from":[108,212],"then":[113],"transferred":[114,171],"semantically":[117],"guided":[124],"by":[125,173],"map,":[128],"finally,":[130],"replaced":[135],"with":[136],"features.":[140],"Notably,":[141],"calculate":[147],"maps":[149],"separately":[150],"for":[151],"achieving":[157,215,250],"more":[158],"precise":[159],"alignment.":[161],"Second,":[162],"classifier-free":[165],"guidance,":[167],"enhances":[169],"combining":[174],"color-transferred":[175],"non-color-transferred":[177],"outputs.":[178],"This":[179],"process":[180],"improves":[181],"quality":[183,200],"colorization.":[185],"Our":[186,260],"experimental":[187],"results":[188],"demonstrate":[189],"our":[191,236],"method":[192],"outperforms":[193],"existing":[194],"techniques":[195],"in":[196],"terms":[197],"fidelity":[202],"reference.":[205],"Specifically,":[206],"use":[208],"335":[209],"input-reference":[210],"pairs":[211,243],"previous":[213],"research,":[214],"FID":[217,252],"95.27":[219],"(image":[220],"quality)":[221],"SI-FID":[224,257],"5.51":[226],"(fidelity":[227],"reference).":[230],"In":[231],"addition,":[232],"evaluate":[234],"novel":[237],"dataset,":[238],"consists":[240],"100":[242],"natural":[245],"photos":[246],"historical":[248],"paintings,":[249],"219.05":[254],"7.94.":[259],"source":[261],"code":[262],"available":[264],"at":[265],"https://github.com/satoshi-kosugi/powerful-attention.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-05-13T08:25:38.343686","created_date":"2025-10-10T00:00:00"}