{"id":"https://openalex.org/W7138971517","doi":"https://doi.org/10.48550/arxiv.2603.16649","title":"Mixture of Style Experts for Diverse Image Stylization","display_name":"Mixture of Style Experts for Diverse Image Stylization","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7138971517","doi":"https://doi.org/10.48550/arxiv.2603.16649"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.16649","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130181807","display_name":"Shihao Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhu, Shihao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106582398","display_name":"Ziheng Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Ziheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051003291","display_name":"Yijia Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Yijia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129866831","display_name":"Qilong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qilong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129772343","display_name":"Mi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Mi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129928813","display_name":"Bo Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129912059","display_name":"Ming-Ming Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Ming-Ming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123948518","display_name":"Qibin Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Qibin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5130181807"],"corresponding_institution_ids":[],"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":null,"last_page":null},"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":0.9708999991416931,"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":0.9708999991416931,"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":0.004900000058114529,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.003100000089034438,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7458000183105469},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.635699987411499},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5049999952316284},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4212000072002411},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4016999900341034},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3910999894142151}],"concepts":[{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7458000183105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250999808311462},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.635699987411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6297000050544739},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47690001130104065},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3910999894142151},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.16649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.7214003205299377,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"stylization":[1],"has":[2],"advanced":[3],"significantly,":[4],"yet":[5],"existing":[6,104],"methods":[7],"are":[8,122],"limited":[9],"to":[10,47,61,71,95,114],"color-driven":[11],"transformations,":[12],"neglecting":[13],"complex":[14],"semantics":[15,108],"and":[16,109,119],"material":[17,110],"details.":[18],"We":[19],"introduce":[20],"StyleExpert,":[21],"a":[22,35,52,63],"semantic-aware":[23],"framework":[24,33],"based":[25],"on":[26,40],"the":[27,75,125],"Mixture":[28],"of":[29,44],"Experts":[30],"(MoE).":[31],"Our":[32,117],"employs":[34],"unified":[36],"style":[37],"encoder,":[38],"trained":[39],"our":[41,82],"large-scale":[42],"dataset":[43],"content-style-stylized":[45],"triplets,":[46],"embed":[48],"diverse":[49,86],"styles":[50,70,87],"into":[51],"consistent":[53],"latent":[54],"space.":[55],"This":[56],"embedding":[57],"is":[58],"then":[59],"used":[60],"condition":[62],"similarity-aware":[64],"gating":[65],"mechanism,":[66],"which":[67],"dynamically":[68],"routes":[69],"specialized":[72],"experts":[73],"within":[74],"MoE":[76,80],"architecture.":[77],"Leveraging":[78],"this":[79],"architecture,":[81],"method":[83],"adeptly":[84],"handles":[85],"spanning":[88],"multiple":[89],"semantic":[90],"levels,":[91],"from":[92],"shallow":[93],"textures":[94],"deep":[96],"semantics.":[97],"Extensive":[98],"experiments":[99],"show":[100],"that":[101],"StyleExpert":[102],"outperforms":[103],"approaches":[105],"in":[106],"preserving":[107],"details,":[111],"while":[112],"generalizing":[113],"unseen":[115],"styles.":[116],"code":[118],"collected":[120],"images":[121],"available":[123],"at":[124],"project":[126],"page:":[127],"https://hh-lg.github.io/StyleExpert-Page/.":[128]},"counts_by_year":[],"updated_date":"2026-03-21T06:30:42.041108","created_date":"2026-03-20T00:00:00"}