{"id":"https://openalex.org/W7118876859","doi":"https://doi.org/10.1109/tmm.2026.3651101","title":"ColView: Consistent Text-Guided Grayscale Scene Colorization From Multi-View Images","display_name":"ColView: Consistent Text-Guided Grayscale Scene Colorization From Multi-View Images","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118876859","doi":"https://doi.org/10.1109/tmm.2026.3651101"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651101","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5113005982","display_name":"Chaochao Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaochao Niu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-3727-5300","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102776884","display_name":"Ming Tao","orcid":"https://orcid.org/0000-0002-4662-7170"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Tao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4662-7170","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044697325","display_name":"Bing-Kun Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101552487","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03477843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3328","last_page":"3338"},"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":0.7979999780654907,"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":0.7979999780654907,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.04670000076293945,"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"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.03830000013113022,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/grayscale","display_name":"Grayscale","score":0.8621000051498413},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49709999561309814},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4399000108242035},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.40049999952316284},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.397599995136261},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36890000104904175},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.3671000003814697},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.36640000343322754},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3634999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.869700014591217},{"id":"https://openalex.org/C78201319","wikidata":"https://www.wikidata.org/wiki/Q685727","display_name":"Grayscale","level":3,"score":0.8621000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7404000163078308},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6435999870300293},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49709999561309814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.397599995136261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3447999954223633},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651101","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5851403343","display_name":null,"funder_award_id":"62325206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2114770744","https://openalex.org/W2133665775","https://openalex.org/W2475287302","https://openalex.org/W2962785568","https://openalex.org/W2963145877","https://openalex.org/W2963502052","https://openalex.org/W2964288609","https://openalex.org/W3157201319","https://openalex.org/W3180107964","https://openalex.org/W3215769467","https://openalex.org/W4200150166","https://openalex.org/W4283803607","https://openalex.org/W4311802540","https://openalex.org/W4312318483","https://openalex.org/W4312538174","https://openalex.org/W4312836763","https://openalex.org/W4312933868","https://openalex.org/W4378450585","https://openalex.org/W4385318467","https://openalex.org/W4386072096","https://openalex.org/W4386075604","https://openalex.org/W4386075616","https://openalex.org/W4386076215","https://openalex.org/W4389539682","https://openalex.org/W4390872653","https://openalex.org/W4391341374","https://openalex.org/W4393149883","https://openalex.org/W4402125949","https://openalex.org/W4404536255","https://openalex.org/W4404641928","https://openalex.org/W4405003283","https://openalex.org/W7133227969","https://openalex.org/W7133244582"],"related_works":[],"abstract_inverted_index":{"The":[0],"colorization":[1,28,50,101,108,131,154],"of":[2,56,109],"scenes":[3,111],"from":[4,80,112],"multi-view":[5,65,113,147,152],"grayscale":[6,99,110,114],"images":[7],"plays":[8],"a":[9,94,151],"crucial":[10],"role":[11],"in":[12],"applications":[13],"such":[14],"as":[15,125,196],"augmented":[16],"reality":[17],"and":[18,72,76,85,106,182,220,225],"virtual":[19],"exhibitions.":[20],"Existing":[21],"methods":[22,46],"combine":[23],"NeRF":[24],"with":[25],"an":[26],"automatic":[27,105],"model,":[29],"averaging":[30],"multiple":[31],"colorized":[32],"patches":[33],"to":[34,53,63,128,136,145,187],"reduce":[35],"inconsistency.":[36],"However,":[37],"they":[38],"still":[39],"face":[40],"three":[41,166],"key":[42,167],"limitations:":[43],"(1)":[44],"Current":[45],"cannot":[47],"produce":[48],"diverse":[49],"results":[51,211],"due":[52],"the":[54,126,130],"lack":[55],"multimodal":[57],"conditional":[58],"inputs,":[59],"(2)":[60],"They":[61],"struggle":[62],"maintain":[64],"consistency":[66],"caused":[67],"by":[68],"unreliable":[69],"geometric":[70],"correspondence":[71,180],"ineffective":[73],"propagation":[74],"mechanisms,":[75],"(3)":[77],"Computational":[78],"inefficiency":[79],"NeRF's":[81],"dense":[82],"ray":[83],"sampling":[84],"numerical":[86],"integration.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91,121,149,191],"propose":[92],"ColView,":[93],"unified":[95],"framework":[96],"for":[97,117,172,178],"text-guided":[98],"scene":[100],"that":[102,156,213],"achieves":[103,216],"both":[104],"controllable":[107],"images.":[115],"First,":[116],"flexible":[118],"color":[119],"control,":[120],"leverage":[122],"text":[123],"description":[124],"input":[127],"guide":[129],"process,":[132],"which":[133],"allows":[134],"users":[135],"specify":[137],"desired":[138],"colors":[139],"through":[140],"natural":[141],"language":[142],"descriptions.":[143],"Second,":[144],"ensure":[146],"consistency,":[148],"introduce":[150],"consistent":[153],"module":[155,164],"explicitly":[157],"models":[158,226],"dependencies":[159],"between":[160],"different":[161],"views.":[162],"This":[163,200],"follows":[165],"steps:":[168],"cross-view":[169],"attention":[170],"mechanism":[171],"collaborative":[173],"key-view":[174],"colorization,":[175],"feature":[176,184],"matching":[177],"inter-view":[179],"establishment,":[181],"correspondence-guided":[183],"propagation.":[185],"Third,":[186],"improve":[188],"computational":[189,221],"efficiency,":[190],"adopt":[192],"3D":[193],"Gaussian":[194],"Splatting":[195],"our":[197,214],"underlying":[198],"representation.":[199],"explicit":[201],"point-based":[202],"representation":[203],"renders":[204],"significantly":[205],"faster":[206],"than":[207],"NeRF.":[208],"Extensive":[209],"experimental":[210],"demonstrate":[212],"method":[215],"superior":[217],"visual":[218],"quality":[219],"efficiency.":[222],"Our":[223],"code":[224],"are":[227],"publicly":[228],"available":[229],"at":[230],"<uri":[231],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[232],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/ChchNiu/ColView</uri>.":[233]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-08T00:00:00"}