{"id":"https://openalex.org/W4408346027","doi":"https://doi.org/10.1109/icassp49660.2025.10889203","title":"DiffuseFIST: A Fast Image-guided Style Transfer Method for Adapting Large-scale Diffusion Models","display_name":"DiffuseFIST: A Fast Image-guided Style Transfer Method for Adapting Large-scale Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408346027","doi":"https://doi.org/10.1109/icassp49660.2025.10889203"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5108260015","display_name":"Miaomiao Dai","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":"Miaomiao Dai","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031210225","display_name":"Qianyu Zhou","orcid":"https://orcid.org/0000-0002-5331-050X"},"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":"Qianyu Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066573999","display_name":"Ran Yi","orcid":"https://orcid.org/0000-0003-3266-3805"},"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":"Ran Yi","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"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":"Lizhuang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,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":"1","last_page":"5"},"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":0.9120000004768372,"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":0.9120000004768372,"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/computer-science","display_name":"Computer science","score":0.6874863505363464},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5940279364585876},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5302842259407043},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5239522457122803},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5159741044044495},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45250120759010315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4189271926879883},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3364713788032532},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07251045107841492},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.06375432014465332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6874863505363464},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5940279364585876},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5302842259407043},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5239522457122803},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5159741044044495},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45250120759010315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189271926879883},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3364713788032532},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07251045107841492},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.06375432014465332},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2561196672","https://openalex.org/W2603777577","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2963095605","https://openalex.org/W3176935213","https://openalex.org/W3191805365","https://openalex.org/W3202767484","https://openalex.org/W3204777666","https://openalex.org/W4296900456","https://openalex.org/W4312365264","https://openalex.org/W4312933868","https://openalex.org/W4313029666","https://openalex.org/W4382240160","https://openalex.org/W4386071613","https://openalex.org/W4386113271","https://openalex.org/W4390872836","https://openalex.org/W4390873054","https://openalex.org/W4390874199","https://openalex.org/W4390874265","https://openalex.org/W4392909930","https://openalex.org/W4392909960","https://openalex.org/W4402667886","https://openalex.org/W6636751772","https://openalex.org/W6731043416","https://openalex.org/W6738438352","https://openalex.org/W6765779288","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6803459629","https://openalex.org/W6837916454","https://openalex.org/W6845433216","https://openalex.org/W6849177959","https://openalex.org/W6859225448"],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W2349768204","https://openalex.org/W4313326281","https://openalex.org/W574867512","https://openalex.org/W2387271333","https://openalex.org/W581389233","https://openalex.org/W2361120309","https://openalex.org/W632157940","https://openalex.org/W2387981414","https://openalex.org/W2361546210"],"abstract_inverted_index":{"Pre-trained":[0],"text-to-image":[1],"(T2I)":[2],"synthesis":[3],"diffusion":[4,46,62],"models":[5],"(DM)":[6],"have":[7],"shown":[8],"remarkable":[9],"capabilities":[10],"in":[11,29,42,164],"generating":[12],"diverse":[13],"images.":[14],"However,":[15],"they":[16],"struggle":[17],"to":[18,24,39,72,87,100,146],"satisfy":[19],"the":[20,105,115,149],"user\u2019s":[21],"requirements":[22],"due":[23,38],"(i)":[25],"text\u2019s":[26],"inherent":[27],"imprecision":[28],"expressing":[30],"specific":[31],"styles":[32],"and":[33,76,81,90,112,130,142,153,167],"(ii)":[34],"generation":[35],"is":[36],"time-consuming":[37],"many":[40],"iterations":[41],"reverse":[43,74],"process":[44,75],"of":[45,132],"models.":[47],"To":[48],"address":[49],"these":[50],"issues,":[51],"we":[52,94,118,136],"propose":[53],"a":[54],"fast":[55],"style":[56,92,169],"transfer":[57,170],"method":[58,160],"adopting":[59],"pre-trained":[60],"large-scale":[61],"models,":[63],"dubbed":[64],"as":[65,84],"DiffuseFIST,":[66],"which":[67,125],"adds":[68],"T-small":[69],"(300)":[70],"noise":[71],"accelerate":[73],"solely":[77],"requires":[78],"real-world":[79],"images":[80,83],"artistic":[82],"input.":[85],"Specifically,":[86],"preserve":[88],"content":[89],"prevent":[91],"leakage,":[93],"introduce":[95],"Content":[96],"Injection":[97],"(CI)":[98],"strategy":[99,124],"achieve":[101],"fine-grained":[102],"control":[103,131],"over":[104],"generated":[106],"structure":[107],"by":[108],"manipulating":[109],"spatial":[110],"features":[111],"self-attention":[113],"inside":[114],"model.":[116],"Furthermore,":[117],"design":[119],"Iterative":[120],"Style":[121],"Guidance":[122],"(ISG)":[123],"allows":[126],"explicit":[127],"user":[128],"guidance":[129],"stylization":[133],"tradeoffs.":[134],"Finally,":[135],"initialize":[137],"latent":[138],"variable":[139],"with":[140,148],"Whitening":[141],"Coloring":[143],"Transform":[144],"(WCT)":[145],"deal":[147],"disharmonious":[150],"color.":[151],"Qualitative":[152],"quantitative":[154],"experiments":[155],"demonstrate":[156],"that":[157],"our":[158],"proposed":[159],"surpasses":[161],"state-of-the-art":[162],"methods":[163],"both":[165],"conventional":[166],"diffusion-based":[168],"methods.":[171]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}