{"id":"https://openalex.org/W4400573541","doi":"https://doi.org/10.1145/3641519.3657509","title":"Versatile Vision Foundation Model for Image and Video Colorization","display_name":"Versatile Vision Foundation Model for Image and Video Colorization","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400573541","doi":"https://doi.org/10.1145/3641519.3657509"},"language":"en","primary_location":{"id":"doi:10.1145/3641519.3657509","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers 24","raw_type":"proceedings-article"},"type":"article","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/A5093299981","display_name":"Vukasin Bozic","orcid":"https://orcid.org/0009-0007-7484-4483"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Vukasin Bozic","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075419871","display_name":"Abdelaziz Djelouah","orcid":"https://orcid.org/0000-0002-0727-1247"},"institutions":[{"id":"https://openalex.org/I4210137357","display_name":"Walt Disney (Switzerland)","ror":"https://ror.org/04h1x1p54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210137357","https://openalex.org/I4210142140"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Abdelaziz Djelouah","raw_affiliation_strings":["Disney Research Studios, Switzerland"],"affiliations":[{"raw_affiliation_string":"Disney Research Studios, Switzerland","institution_ids":["https://openalex.org/I4210137357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354651","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-2381-6067"},"institutions":[{"id":"https://openalex.org/I4210137357","display_name":"Walt Disney (Switzerland)","ror":"https://ror.org/04h1x1p54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210137357","https://openalex.org/I4210142140"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Disney Research Studios, Switzerland"],"affiliations":[{"raw_affiliation_string":"Disney Research Studios, Switzerland","institution_ids":["https://openalex.org/I4210137357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052236177","display_name":"Radu Timofte","orcid":"https://orcid.org/0000-0002-1478-0402"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Radu Timofte","raw_affiliation_strings":["University of Wurzburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Wurzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033076979","display_name":"Markus Gro\u00df","orcid":"https://orcid.org/0009-0003-9324-779X"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I4210137357","display_name":"Walt Disney (Switzerland)","ror":"https://ror.org/04h1x1p54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210137357","https://openalex.org/I4210142140"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Markus Gross","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland and Disney Research Studios, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland and Disney Research Studios, Switzerland","institution_ids":["https://openalex.org/I4210137357","https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052388616","display_name":"Christopher Schroers","orcid":"https://orcid.org/0000-0003-1473-1878"},"institutions":[{"id":"https://openalex.org/I4210137357","display_name":"Walt Disney (Switzerland)","ror":"https://ror.org/04h1x1p54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210137357","https://openalex.org/I4210142140"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christopher Schroers","raw_affiliation_strings":["Disney Research Studios, Switzerland"],"affiliations":[{"raw_affiliation_string":"Disney Research Studios, Switzerland","institution_ids":["https://openalex.org/I4210137357"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5093299981"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":1.9689,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87412562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9965000152587891,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9965000152587891,"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/T11666","display_name":"Color Science and Applications","score":0.994700014591217,"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":0.9926000237464905,"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":0.7213246822357178},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6967610716819763},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6802316904067993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6317562460899353},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.536842942237854},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.44133108854293823},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06016308069229126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213246822357178},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6967610716819763},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6802316904067993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6317562460899353},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.536842942237854},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.44133108854293823},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06016308069229126},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641519.3657509","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers 24","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":48,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1861492603","https://openalex.org/W2046119925","https://openalex.org/W2159269332","https://openalex.org/W2240798854","https://openalex.org/W2295537950","https://openalex.org/W2326925005","https://openalex.org/W2461158874","https://openalex.org/W2562457735","https://openalex.org/W2584890299","https://openalex.org/W2809852002","https://openalex.org/W2962785568","https://openalex.org/W2963145877","https://openalex.org/W2963904861","https://openalex.org/W2979841973","https://openalex.org/W2989277455","https://openalex.org/W2994546229","https://openalex.org/W3010626953","https://openalex.org/W3034583007","https://openalex.org/W3034838697","https://openalex.org/W3135367836","https://openalex.org/W3193744354","https://openalex.org/W3207381926","https://openalex.org/W3212516020","https://openalex.org/W4210445907","https://openalex.org/W4226227850","https://openalex.org/W4230012894","https://openalex.org/W4235375376","https://openalex.org/W4246399762","https://openalex.org/W4311805952","https://openalex.org/W4311806086","https://openalex.org/W4312783155","https://openalex.org/W4312836763","https://openalex.org/W4312898263","https://openalex.org/W4312933868","https://openalex.org/W4313191495","https://openalex.org/W4319300802","https://openalex.org/W4384151580","https://openalex.org/W4385800714","https://openalex.org/W4386057725","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4390873054","https://openalex.org/W4390873774","https://openalex.org/W6600669965","https://openalex.org/W6752851532","https://openalex.org/W6816071129","https://openalex.org/W6855872688"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Image":[0],"and":[1,18,65,94,115,138],"video":[2,96],"colorization":[3,64,79,85,147],"are":[4,111],"among":[5],"the":[6,108,122,134,158],"most":[7,35],"common":[8],"problems":[9],"in":[10,144,174],"image":[11,63,93],"restoration.":[12],"This":[13],"is":[14,130,157],"an":[15],"ill-posed":[16],"problem":[17],"a":[19,51,67,71,118,163,179],"wide":[20,72,164],"variety":[21,73],"of":[22,74,136,181],"methods":[23,172],"have":[24],"been":[25],"proposed,":[26],"ranging":[27],"from":[28],"more":[29,113],"traditional":[30],"computer":[31],"vision":[32],"strategies":[33],"to":[34,189],"recent":[36],"development":[37],"with":[38,80],"transformer-based":[39],"or":[40,91,169],"generative":[41],"neural":[42],"network":[43],"models.":[44],"In":[45],"this":[46,131],"work":[47],"we":[48,149],"show":[49],"how":[50],"latent":[52],"diffusion":[53,103,192],"model,":[54],"pre-trained":[55,191],"on":[56],"text-to-image":[57],"synthesis,":[58],"can":[59],"be":[60,187],"finetuned":[61],"for":[62,70,105],"provide":[66],"flexible":[68],"solution":[69],"scenarios:":[75],"high":[76],"quality":[77],"direct":[78],"diverse":[81],"results,":[82],"user":[83],"guided":[84],"through":[86],"colors":[87],"hints,":[88],"text":[89],"prompts":[90],"reference":[92],"finally":[95],"colorization.":[97],"Some":[98],"works":[99],"already":[100],"investigated":[101],"using":[102],"models":[104],"colorization,":[106],"however":[107],"proposed":[109],"solutions":[110],"often":[112],"complex":[114],"require":[116],"training":[117],"side":[119],"model":[120,156],"guiding":[121],"denoising":[123],"process":[124],"(\u00e0":[125],"la":[126],"ControlNet).":[127],"Not":[128],"only":[129,159],"approach":[132,160],"increasing":[133],"number":[135],"parameters":[137],"compute":[139],"time,":[140],"it":[141],"also":[142],"results":[143],"sub":[145],"optimal":[146],"as":[148],"show.":[150],"Our":[151],"evaluation":[152],"demonstrates":[153],"that":[154,161],"our":[155],"offers":[162],"flexibility":[165],"while":[166],"either":[167],"matching":[168],"outperforming":[170],"existing":[171],"specialized":[173],"each":[175],"sub-task,":[176],"by":[177],"proposing":[178],"group":[180],"universal,":[182],"architecture-agnostic":[183],"mechanisms":[184],"which":[185],"could":[186],"applied":[188],"any":[190],"model.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}