{"id":"https://openalex.org/W4390833441","doi":"https://doi.org/10.48550/arxiv.2401.05870","title":"HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models","display_name":"HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models","publication_year":2024,"publication_date":"2024-01-11","ids":{"openalex":"https://openalex.org/W4390833441","doi":"https://doi.org/10.48550/arxiv.2401.05870"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2401.05870","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.05870","pdf_url":"https://arxiv.org/pdf/2401.05870","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.05870","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101670955","display_name":"Hanzhang Wang","orcid":"https://orcid.org/0000-0002-4649-7361","observed_orcids":["https://orcid.org/0000-0002-4649-7361","https://orcid.org/0009-0006-4088-5984"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hanzhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324809","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0001-6350-5645","observed_orcids":["https://orcid.org/0000-0001-6350-5645"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061474693","display_name":"Jinze Yang","orcid":"https://orcid.org/0000-0001-5900-1487","observed_orcids":["https://orcid.org/0000-0001-5900-1487"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jinze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113095187","display_name":"Zhongrui Yu","orcid":"https://orcid.org/0009-0007-7709-8973","observed_orcids":["https://orcid.org/0009-0007-7709-8973"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Zhongrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066773635","display_name":"Zeke Xie","orcid":"https://orcid.org/0000-0003-4766-435X","observed_orcids":["https://orcid.org/0000-0003-4766-435X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Zeke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tian, Lei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112673776","display_name":"Xinyan Xiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Xinyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087165831","display_name":"Junjun Jiang","orcid":"https://orcid.org/0000-0002-5694-505X","observed_orcids":["https://orcid.org/0000-0002-5694-505X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Junjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654390","display_name":"Xianming Liu","orcid":"https://orcid.org/0000-0002-8857-1785","observed_orcids":["https://orcid.org/0000-0002-8857-1785"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xianming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101359729","display_name":"Mingming Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Mingming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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":1.0,"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":1.0,"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":0.0,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0,"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/arbitrary-style-transfer","display_name":"arbitrary style transfer","score":0.9959999918937683},{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.8610000014305115},{"id":"https://openalex.org/keywords/video-style-transfer","display_name":"video style transfer","score":0.871999979019165},{"id":"https://openalex.org/keywords/temporal-coherence","display_name":"temporal coherence","score":0.7879999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760627269744873},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7120466232299805},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.5396108627319336},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5221786499023438},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.504656195640564},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4788648784160614},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4378575384616852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4179002642631531},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32350990176200867},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09213617444038391},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2401.05870","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.05870","pdf_url":"https://arxiv.org/pdf/2401.05870","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.05870","doi":"https://doi.org/10.48550/arxiv.2401.05870","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.05870","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.05870","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.05870","pdf_url":"https://arxiv.org/pdf/2401.05870","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W590788508","https://openalex.org/W4235873430","https://openalex.org/W2611974471","https://openalex.org/W4313233093","https://openalex.org/W2133028525","https://openalex.org/W4306381730","https://openalex.org/W4229060448","https://openalex.org/W2358082531","https://openalex.org/W2589976903","https://openalex.org/W2981692913"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,12,65,75,102,109,161],"Arbitrary":[3],"Style":[4],"Transfer":[5],"(AST)":[6],"is":[7,60,63,83,105,145],"injecting":[8],"the":[9,26,34,68,79,118,159,180],"artistic":[10],"features":[11],"a":[13,17,54],"style":[14,29,98,124],"reference":[15],"into":[16],"given":[18],"image/video.":[19],"Existing":[20],"methods":[21,183],"usually":[22],"focus":[23],"on":[24,86],"pursuing":[25],"balance":[27],"between":[28],"and":[30,39,43,91,97,126,166],"content,":[31],"whereas":[32],"ignoring":[33],"significant":[35],"demand":[36],"for":[37,147],"flexible":[38],"customized":[40],"stylization":[41,69,163,188],"results":[42,70,120],"thereby":[44],"limiting":[45],"their":[46],"practical":[47],"application.":[48],"To":[49],"address":[50],"this":[51],"critical":[52],"issue,":[53],"novel":[55,142],"AST":[56],"approach":[57],"namely":[58],"HiCAST":[59,178],"proposed,":[61],"which":[62,112,152],"capable":[64],"explicitly":[66],"customizing":[67],"according":[71],"to":[72,94,115,137],"various":[73],"source":[74],"semantic":[76],"clues.":[77],"In":[78],"specific,":[80],"our":[81,135,177],"model":[82,136,150],"constructed":[84],"based":[85],"Latent":[87],"Diffusion":[88],"Model":[89],"(LDM)":[90],"elaborately":[92],"designed":[93],"absorb":[95],"content":[96],"instance":[99],"as":[100,169,171],"conditions":[101],"LDM.":[103,130],"It":[104],"characterized":[106],"by":[107,121],"introducing":[108],"\\textit{Style":[110],"Adapter},":[111],"allows":[113],"user":[114,173],"flexibly":[116],"manipulate":[117],"output":[119],"aligning":[122],"multi-level":[123],"information":[125],"intrinsic":[127],"knowledge":[128],"in":[129,158,184],"Lastly,":[131],"we":[132],"further":[133],"extend":[134],"perform":[138],"video":[139,148],"AST.":[140],"A":[141],"learning":[143],"objective":[144],"leveraged":[146],"diffusion":[149],"training,":[151],"significantly":[153],"improve":[154],"cross-frame":[155],"temporal":[156],"consistency":[157],"premise":[160],"maintaining":[162],"strength.":[164],"Qualitative":[165],"quantitative":[167],"comparisons":[168],"well":[170],"comprehensive":[172],"studies":[174],"demonstrate":[175],"that":[176],"outperforms":[179],"existing":[181],"SoTA":[182],"generating":[185],"visually":[186],"plausible":[187],"results.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-02T10:15:12.560889","created_date":"2024-01-13T00:00:00"}