{"id":"https://openalex.org/W7160237557","doi":"https://doi.org/10.1109/wacv61042.2026.00452","title":"Towards Photorealistic Style Transfer with Multimodal Guidance and Robustness to Content Images in Arbitrary Styles","display_name":"Towards Photorealistic Style Transfer with Multimodal Guidance and Robustness to Content Images in Arbitrary Styles","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160237557","doi":"https://doi.org/10.1109/wacv61042.2026.00452"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111072785","display_name":"Ruikai Zhou","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":"Ruikai Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687681","display_name":"Liu Y","orcid":"https://orcid.org/0000-0002-0994-0109"},"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":"Yating Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071486932","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0002-1817-9884"},"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":"Yi Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4651","last_page":"4660"},"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":0.9603000283241272,"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":0.9603000283241272,"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":0.006500000134110451,"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":0.004600000102072954,"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/robustness","display_name":"Robustness (evolution)","score":0.7195000052452087},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.3637000024318695},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32850000262260437},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.2881999909877777}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7195000052452087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6255999803543091},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5950999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849999785423279},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.24580000340938568},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.241799995303154}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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/W1861492603","https://openalex.org/W2050222448","https://openalex.org/W2129112648","https://openalex.org/W2141015396","https://openalex.org/W2604721644","https://openalex.org/W2963683323","https://openalex.org/W2969803502","https://openalex.org/W2989045104","https://openalex.org/W2997418011","https://openalex.org/W3107989310","https://openalex.org/W3209554182","https://openalex.org/W3216156094","https://openalex.org/W3216352822","https://openalex.org/W4214926101","https://openalex.org/W4230472795","https://openalex.org/W4286611278","https://openalex.org/W4312502087","https://openalex.org/W4312740349","https://openalex.org/W4382459069","https://openalex.org/W4382462760","https://openalex.org/W4386065395","https://openalex.org/W4386065831","https://openalex.org/W4386071613","https://openalex.org/W4386076215","https://openalex.org/W4390871856","https://openalex.org/W4393156269","https://openalex.org/W4394597461","https://openalex.org/W4394625571","https://openalex.org/W4399919740","https://openalex.org/W4402667886","https://openalex.org/W4402703083","https://openalex.org/W4402715992","https://openalex.org/W4406627735","https://openalex.org/W4406753695","https://openalex.org/W4409263797","https://openalex.org/W4412102569"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"photorealistic":[1,86,202],"style":[2,21,29,87,122,137,203],"transfer":[3,88],"methods":[4,58],"are":[5,40],"broadly":[6],"categorized":[7],"into":[8],"two":[9],"groups:":[10],"image-guided":[11,16,192],"and":[12,93,176,193],"text-guided":[13,50,57,147,194],"approaches.":[14],"The":[15],"paradigm":[17,51],"requires":[18],"a":[19,83,111,165],"reference":[20],"image,":[22],"which":[23,170],"is":[24,30],"superior":[25],"when":[26,71],"the":[27,49,63,115,120,124,128,136,146,155],"target":[28],"difficult":[31],"to":[32,61],"define":[33],"precisely":[34],"with":[35,150],"text.":[36],"Unfortunately,":[37],"such":[38],"references":[39],"not":[41],"always":[42],"available":[43],"in":[44,105,190],"practical":[45],"scenarios.":[46],"In":[47,78],"contrast,":[48],"offers":[52],"greater":[53],"flexibility.":[54],"However,":[55],"existing":[56],"often":[59],"fail":[60],"preserve":[62],"details":[64],"of":[65,95],"content":[66,72,103,125],"images":[67,73,104],"or":[68,141],"perform":[69],"poorly":[70],"deviate":[74],"from":[75,123],"normal":[76],"style.":[77],"this":[79,151],"paper,":[80],"we":[81,109,153,163,197],"present":[82],"novel":[84],"multimodal-guided":[85],"framework,":[89],"supporting":[90],"flexible":[91],"switching":[92],"fusion":[94],"both":[96,191],"modalities":[97],"while":[98],"ensuring":[99],"robust":[100],"performance":[101,189],"across":[102],"arbitrary":[106],"styles.":[107],"Specifically,":[108],"adopt":[110],"two-stage":[112],"pipeline.":[113],"First,":[114],"Style":[116,129,158],"Removal":[117],"Module":[118,131],"removes":[119],"original":[121],"image.":[126],"Then,":[127],"Injection":[130,159],"applies":[132],"stylization":[133],"based":[134],"on":[135],"guidance":[138],"(image,":[139],"text,":[140],"their":[142],"fusion).":[143],"To":[144],"make":[145],"branch":[148],"compatible":[149],"pipeline,":[152],"propose":[154],"Image-Assisted":[156],"Textual":[157],"(IATSI)":[160],"strategy.":[161],"Additionally,":[162],"design":[164],"Dual-Residual":[166],"Adaptive":[167],"MLP":[168],"(DRA-MLP),":[169],"exhibits":[171],"strong":[172],"color":[173],"mapping":[174],"capability":[175],"avoids":[177],"spatial":[178],"distortions.":[179],"Extensive":[180],"experiments":[181],"show":[182],"that":[183],"our":[184],"method":[185],"achieves":[186],"state-of-the-art":[187],"(SOTA)":[188],"settings.":[195],"Moreover,":[196],"innovatively":[198],"implement":[199],"multimodal":[200],"fusion-guided":[201],"transfer,":[204],"achieving":[205],"promising":[206],"results.":[207]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}