{"id":"https://openalex.org/W4409761309","doi":"https://doi.org/10.26599/cvm.2025.9450419","title":"IIDM: Image-to-Image Diffusion Model for Semantic Image Synthesis","display_name":"IIDM: Image-to-Image Diffusion Model for Semantic Image Synthesis","publication_year":2025,"publication_date":"2025-04-01","ids":{"openalex":"https://openalex.org/W4409761309","doi":"https://doi.org/10.26599/cvm.2025.9450419"},"language":"en","primary_location":{"id":"doi:10.26599/cvm.2025.9450419","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450419","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/cvm.2025.9450419","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100415287","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0002-5399-6214"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["School of Artificial Intelligence, Sun Yat-sen University,Zhuhai,China,519082","School of Artificial Intelligence, Sun Yat-sen University, Zhuhai 519082, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-sen University,Zhuhai,China,519082","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai 519082, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021121018","display_name":"Xiaobin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Chang","raw_affiliation_strings":["School of Artificial Intelligence, Sun Yat-sen University,Zhuhai,China,519082","School of Artificial Intelligence, Sun Yat-sen University, Zhuhai 519082, China; Key Laboratory of Intelligent Assessment Technology for Sustainable Tourism, Ministry of Culture and Tourism, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-sen University,Zhuhai,China,519082","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai 519082, China; Key Laboratory of Intelligent Assessment Technology for Sustainable Tourism, Ministry of Culture and Tourism, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":2.2966,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87909532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"11","issue":"2","first_page":"423","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9848999977111816,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9848999977111816,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9735999703407288,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9341999888420105,"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/image","display_name":"Image (mathematics)","score":0.6833728551864624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5702224373817444},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.48397207260131836},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.46561551094055176},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44482994079589844},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.43551182746887207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42718109488487244}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6833728551864624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5702224373817444},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.48397207260131836},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.46561551094055176},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44482994079589844},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.43551182746887207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42718109488487244}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/cvm.2025.9450419","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450419","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:733ee5695ca34269b8c47ff3ce3533ca","is_oa":true,"landing_page_url":"https://doaj.org/article/733ee5695ca34269b8c47ff3ce3533ca","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Visual Media, Vol 11, Iss 2, Pp 423-429 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/cvm.2025.9450419","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450419","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2255322211","display_name":null,"funder_award_id":"62106289","funder_id":"https://openalex.org/F4320333688","funder_display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320333688","display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2129112648","https://openalex.org/W2754213847","https://openalex.org/W2962974533","https://openalex.org/W2990269423","https://openalex.org/W3096831136","https://openalex.org/W3100341797","https://openalex.org/W3124998760","https://openalex.org/W3158252298","https://openalex.org/W4214868041","https://openalex.org/W4312933868"],"related_works":["https://openalex.org/W2319989118","https://openalex.org/W1503820821","https://openalex.org/W2285491073","https://openalex.org/W1991998366","https://openalex.org/W3112751614","https://openalex.org/W1995979513","https://openalex.org/W4403759101","https://openalex.org/W4249185555","https://openalex.org/W1999937205","https://openalex.org/W4409132263"],"abstract_inverted_index":{"Semantic":[0],"image":[1,45,51],"synthesis":[2,46],"aims":[3],"to":[4,94],"generate":[5],"high-":[6],"quality":[7],"images":[8,35],"given":[9],"semantic":[10,44],"conditions,":[11],"i.e.,":[12],"segmentation":[13,82],"masks":[14],"and":[15,32,54,74,89,105],"style":[16,66],"reference":[17,67],"images.":[18],"Existing":[19],"methods":[20,120],"widely":[21],"adopt":[22],"generative":[23],"adversarial":[24],"networks":[25],"(GANs).":[26],"GANs":[27],"take":[28],"all":[29],"conditional":[30],"inputs":[31],"directly":[33],"synthesize":[34],"in":[36],"a":[37,58],"single":[38],"forward":[39],"step.":[40],"In":[41],"this":[42],"paper,":[43],"is":[47,55,68,126,141],"treated":[48],"as":[49],"an":[50],"denoising":[52],"task":[53],"handled":[56],"with":[57,71],"novel":[59],"image-to-image":[60],"diffusion":[61],"model":[62,90],"(IIDM).":[63],"Specifically,":[64],"the":[65,97,137],"first":[69],"contaminated":[70],"random":[72],"noise":[73],"then":[75],"progressively":[76],"denoised":[77],"by":[78,81,121],"IIDM,":[79],"guided":[80],"masks.":[83],"Moreover,":[84],"three":[85],"techniques,":[86],"refinement,":[87],"color-transfer,":[88],"ensembles,":[91],"are":[92,101],"proposed":[93],"further":[95],"boost":[96],"generation":[98],"quality.":[99],"They":[100],"plug-in":[102],"inference":[103],"modules":[104],"do":[106],"not":[107],"require":[108],"additional":[109],"training.":[110],"Extensive":[111],"experiments":[112],"show":[113],"that":[114],"our":[115],"IIDM":[116,134],"outperforms":[117],"existing":[118],"state-of-the-art":[119],"clear":[122],"margins.":[123],"Further":[124],"analysis":[125],"provided":[127],"via":[128],"detailed":[129],"demonstrations.":[130],"We":[131],"have":[132],"implemented":[133],"based":[135],"on":[136],"Jittor":[138],"framework;":[139],"code":[140],"available":[142],"at":[143],"https://github.com/ader47/jittor-jieke-semantic_images_synthesis.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}