{"id":"https://openalex.org/W6921955064","doi":"https://doi.org/10.1109/tcsvt.2025.3587757","title":"Canvas: Compositional Generation for Art Painting With Seamless Subject-Driven Infusion","display_name":"Canvas: Compositional Generation for Art Painting With Seamless Subject-Driven Infusion","publication_year":2025,"publication_date":"2025-07-10","ids":{"openalex":"https://openalex.org/W6921955064","doi":"https://doi.org/10.1109/tcsvt.2025.3587757"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3587757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3587757","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yunnan Wang","orcid":"https://orcid.org/0000-0002-5480-4587"},"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":true,"raw_author_name":"Yunnan Wang","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziqiang Li","orcid":null},"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":"Ziqiang Li","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenyao Zhang","orcid":"https://orcid.org/0009-0006-3090-255X"},"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":"Wenyao Zhang","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lexiang Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lexiang Lv","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University (HNU), Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University (HNU), Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zequn Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zequn Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyu Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Shen","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Jin","orcid":"https://orcid.org/0000-0002-1820-8358"},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wenjun Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zeng","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China","institution_ids":["https://openalex.org/I4210165339"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44912199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":"12","first_page":"12238","last_page":"12250"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9229000210762024,"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":0.9229000210762024,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.043699998408555984,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.004699999932199717,"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/subject","display_name":"Subject (documents)","score":0.6827999949455261},{"id":"https://openalex.org/keywords/painting","display_name":"Painting","score":0.6690000295639038},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5446000099182129},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4244999885559082},{"id":"https://openalex.org/keywords/photography","display_name":"Photography","score":0.37049999833106995},{"id":"https://openalex.org/keywords/abstract-art","display_name":"Abstract art","score":0.3646000027656555},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.361299991607666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741000056266785},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.6827999949455261},{"id":"https://openalex.org/C205783811","wikidata":"https://www.wikidata.org/wiki/Q11629","display_name":"Painting","level":2,"score":0.6690000295639038},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5446000099182129},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4456000030040741},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4244999885559082},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C4320435","wikidata":"https://www.wikidata.org/wiki/Q128115","display_name":"Abstract art","level":3,"score":0.3646000027656555},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.361299991607666},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3513999879360199},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.2703000009059906},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3587757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3587757","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3527258163","display_name":null,"funder_award_id":"62302246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6261746788","display_name":null,"funder_award_id":"LQ23F010008","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2946220758","https://openalex.org/W2962785568","https://openalex.org/W3159481202","https://openalex.org/W4311415873","https://openalex.org/W4312388283","https://openalex.org/W4312933868","https://openalex.org/W4312966374","https://openalex.org/W4380905910","https://openalex.org/W4384159712","https://openalex.org/W4385236734","https://openalex.org/W4385245566","https://openalex.org/W4385271055","https://openalex.org/W4385271134","https://openalex.org/W4385271281","https://openalex.org/W4385535331","https://openalex.org/W4386071613","https://openalex.org/W4386072096","https://openalex.org/W4386075993","https://openalex.org/W4386076027","https://openalex.org/W4386076425","https://openalex.org/W4386083141","https://openalex.org/W4387805784","https://openalex.org/W4389160105","https://openalex.org/W4389879878","https://openalex.org/W4390872341","https://openalex.org/W4390872636","https://openalex.org/W4390873054","https://openalex.org/W4390874393","https://openalex.org/W4390874575","https://openalex.org/W4391468134","https://openalex.org/W4392151693","https://openalex.org/W4394625750","https://openalex.org/W4402716004","https://openalex.org/W4402774219","https://openalex.org/W4403791567","https://openalex.org/W4403998619"],"related_works":[],"abstract_inverted_index":{"While":[0],"diffusion-based":[1,96],"art":[2,46,60,180,199],"image":[3,47,182,200],"synthesis":[4],"has":[5],"witnessed":[6],"great":[7],"success":[8],"in":[9,17,183],"terms":[10],"of":[11,38,125,152,198],"quality,":[12],"there":[13],"are":[14,206],"still":[15],"deficiencies":[16],"integrating":[18],"artist-specified":[19],"subjects":[20],"with":[21,89,116,177],"artistic":[22],"style.":[23],"In":[24],"this":[25,81],"paper,":[26],"we":[27,56,83,129],"propose":[28,130],"<italic":[29,75,86,97,100,131,135,159],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[30,76,87,98,101,132,136,160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Canvas</i>,":[31],"a":[32,94,184],"framework":[33],"that":[34,190],"leverages":[35],"the":[36,69,74,106,122,140,143,150,153,158,167,173,178,196],"capabilities":[37],"text-guided":[39],"latent":[40],"diffusion":[41],"models":[42],"(LDMs)":[43],"for":[44],"flexible":[45],"composition":[48],"driven":[49],"by":[50,58,64],"diverse":[51],"customized":[52],"subject":[53,71,118,127],"concepts.":[54,119],"Specifically,":[55],"start":[57],"collecting":[59],"images":[61],"manually":[62],"drawn":[63],"proficient":[65],"artists":[66],"and":[67,204],"annotating":[68],"corresponding":[70],"concepts,":[72,128],"forming":[73],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CreaCulture</i>":[77],"dataset.":[78],"Based":[79],"on":[80,105],"dataset,":[82,109],"build":[84],"our":[85],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Canvas</i>":[88],"two":[90],"generation":[91],"stages.":[92],"Firstly,":[93],"stable":[95],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">stylistic</i>":[99],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">LDM</i>":[102],"is":[103,164],"fine-tuned":[104],"original":[107],"CreaCulture":[108,141],"aiming":[110],"to":[111,138],"generate":[112],"an":[113],"art-style":[114],"background":[115,181],"annotated":[117],"To":[120],"alleviate":[121],"limited":[123],"scope":[124],"tagged":[126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">nature-to-art</i>":[133],"(N2A)":[134],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">transition</i>":[137],"expand":[139],"using":[142],"natural/art":[144],"concepts":[145],"from":[146],"pre-trained/stylistic":[147],"LDM,":[148,169],"facilitating":[149],"fine-tuning":[151],"tailor-made":[154],"concept-derived":[155,168],"LDM.":[156],"Additionally,":[157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Subject-Infused":[161],"Attention":[162],"(SIA)</i>":[163],"integrated":[165],"into":[166],"which":[170],"seamlessly":[171],"composites":[172],"user-specified":[174],"natural":[175],"foreground":[176],"pre-generated":[179],"training-free":[185],"manner.":[186],"Extensive":[187],"experiments":[188],"demonstrate":[189],"Canvas":[191],"outperforms":[192],"state-of-the-art":[193],"alternatives":[194],"under":[195],"setting":[197],"synthesis.":[201],"The":[202],"code":[203],"dataset":[205],"available":[207],"at":[208],"https://github.com/wangyunnan/Canvas.":[209]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
