{"id":"https://openalex.org/W4392903536","doi":"https://doi.org/10.1109/icassp48485.2024.10447821","title":"CartoonDiff: Training-free Cartoon Image Generation with Diffusion Transformer Models","display_name":"CartoonDiff: Training-free Cartoon Image Generation with Diffusion Transformer Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903536","doi":"https://doi.org/10.1109/icassp48485.2024.10447821"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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":"https://openalex.org/A5111333664","display_name":"Feihong He","orcid":null},"institutions":[{"id":"https://openalex.org/I185940356","display_name":"Soochow University","ror":"https://ror.org/05kvm7n82","country_code":"TW","type":"education","lineage":["https://openalex.org/I185940356"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Feihong He","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology","School of Computer Science and Technology, Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology","institution_ids":["https://openalex.org/I185940356"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University","institution_ids":["https://openalex.org/I185940356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438696","display_name":"Gang Li","orcid":"https://orcid.org/0000-0002-4549-293X"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Software","University of Chinese Academy of Sciences","Institute of Software, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Software","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100312943","display_name":"Lingyu Si","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Si","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Software","Institute of Software, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Software","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063085137","display_name":"Leilei Yan","orcid":"https://orcid.org/0000-0002-6909-3052"},"institutions":[{"id":"https://openalex.org/I185940356","display_name":"Soochow University","ror":"https://ror.org/05kvm7n82","country_code":"TW","type":"education","lineage":["https://openalex.org/I185940356"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Leilei Yan","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology","School of Computer Science and Technology, Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology","institution_ids":["https://openalex.org/I185940356"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University","institution_ids":["https://openalex.org/I185940356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028573553","display_name":"Shimeng Hou","orcid":"https://orcid.org/0009-0006-8895-0802"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimeng Hou","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053879237","display_name":"Hong\u2010Wei Dong","orcid":"https://orcid.org/0000-0001-9972-3177"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Dong","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Software","Institute of Software, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Software","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013713640","display_name":"Fanzhang Li","orcid":"https://orcid.org/0000-0003-4318-3081"},"institutions":[{"id":"https://openalex.org/I185940356","display_name":"Soochow University","ror":"https://ror.org/05kvm7n82","country_code":"TW","type":"education","lineage":["https://openalex.org/I185940356"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Fanzhang Li","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology","School of Computer Science and Technology, Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology","institution_ids":["https://openalex.org/I185940356"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University","institution_ids":["https://openalex.org/I185940356"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5111333664"],"corresponding_institution_ids":["https://openalex.org/I185940356"],"apc_list":null,"apc_paid":null,"fwci":2.5586,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90369197,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3825","last_page":"3829"},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9804999828338623,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9785000085830688,"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":0.7942156195640564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6269442439079285},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5313029289245605},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5015959739685059},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46757107973098755},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.4612099230289459},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08063352108001709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942156195640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6269442439079285},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5313029289245605},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5015959739685059},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46757107973098755},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.4612099230289459},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08063352108001709},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3162858518","display_name":null,"funder_award_id":"62176172","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3233909703","display_name":null,"funder_award_id":"2023M733615","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3333612997","display_name":null,"funder_award_id":"62301539","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3740256347","display_name":null,"funder_award_id":"2018YFA0701700","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8971729561","display_name":null,"funder_award_id":"61672364","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2798729263","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W3034491749","https://openalex.org/W3115686843","https://openalex.org/W3121370741","https://openalex.org/W3139248306","https://openalex.org/W3177221875","https://openalex.org/W3200121240","https://openalex.org/W4212774754","https://openalex.org/W4310285364","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4385489809","https://openalex.org/W4387969112","https://openalex.org/W4390872297","https://openalex.org/W6773517458","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6846007759","https://openalex.org/W6846275404"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Image":[0],"cartoonization":[1,18,42,71],"has":[2],"attracted":[3],"significant":[4],"interest":[5],"in":[6,81],"the":[7,15,50,57,62,69,78,96,106],"field":[8],"of":[9,14,25,53,77,99,109],"image":[10,17,41,70,80],"generation.":[11],"However,":[12],"most":[13],"existing":[16],"techniques":[19],"require":[20,87],"re-training":[21],"models":[22,55],"using":[23,43],"images":[24],"cartoon":[26],"style.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,48,67],"present":[32],"CartoonDiff,":[33],"a":[34],"novel":[35],"training-free":[36],"sampling":[37],"approach":[38],"which":[39],"generates":[40],"diffusion":[44,54],"transformer":[45],"models.":[46],"Specifically,":[47],"decompose":[49],"reverse":[51],"process":[52,72],"into":[56],"semantic":[58],"generation":[59,64],"phase":[60],"and":[61],"detail":[63],"phase.":[65],"Furthermore,":[66],"implement":[68],"by":[73],"normalizing":[74],"high-frequency":[75],"signal":[76],"noisy":[79],"specific":[82],"denoising":[83],"steps.":[84],"CartoonDiff":[85],"doesn\u2019t":[86],"any":[88],"additional":[89],"reference":[90],"images,":[91],"complex":[92],"model":[93],"designs,":[94],"or":[95],"tedious":[97],"adjustment":[98],"multiple":[100],"parameters.":[101],"Extensive":[102],"experimental":[103],"results":[104],"show":[105],"powerful":[107],"ability":[108],"our":[110],"CartoonDiff.":[111],"The":[112],"project":[113],"page":[114],"is":[115],"available":[116],"at:":[117],"https://cartoondiff.github.io/":[118]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}