{"id":"https://openalex.org/W4417049785","doi":"https://doi.org/10.1109/iccv51701.2025.01761","title":"DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution","display_name":"DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417049785","doi":"https://doi.org/10.1109/iccv51701.2025.01761"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.23580","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111251783","display_name":"Zheng-Peng Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Peng Duan","raw_affiliation_strings":["VCIP, CS, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462828","display_name":"Jiawei Zhang","orcid":"https://orcid.org/0000-0002-3182-9239"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Zhang","raw_affiliation_strings":["SenseTime Research,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research,China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101882005","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0002-1270-9653"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["VCIP, CS, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613117","display_name":"Ziheng Zhang","orcid":"https://orcid.org/0000-0001-5480-9436"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziheng Zhang","raw_affiliation_strings":["VCIP, CS, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114948990","display_name":"Zheng Xiong","orcid":"https://orcid.org/0009-0002-3453-1478"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Xiong","raw_affiliation_strings":["SenseTime Research,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research,China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039109630","display_name":"Dongqing Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongqing Zou","raw_affiliation_strings":["SenseTime Research,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research,China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109715039","display_name":"Jimmy S. Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jimmy S. Ren","raw_affiliation_strings":["SenseTime Research,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research,China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086639598","display_name":"Chunle Guo","orcid":"https://orcid.org/0000-0002-2432-2026"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunle Guo","raw_affiliation_strings":["VCIP, CS, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034122071","display_name":"Chongyi Li","orcid":"https://orcid.org/0000-0003-2609-2460"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongyi Li","raw_affiliation_strings":["VCIP, CS, Nankai University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, CS, Nankai University,China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":"18948","last_page":"18958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.5030999779701233,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.5030999779701233,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.22010000050067902,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.06030000001192093,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5985000133514404},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5138000249862671},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.48010000586509705},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4731999933719635},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4693000018596649},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4065000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6283000111579895},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5985000133514404},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5138000249862671},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43389999866485596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41819998621940613},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4065000116825104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36550000309944153},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C3017601658","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image enhancement","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2619999945163727}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.23580","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.23580","pdf_url":"https://arxiv.org/pdf/2503.23580","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.23580","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.23580","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.23580","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.23580","pdf_url":"https://arxiv.org/pdf/2503.23580","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5120157993","display_name":null,"funder_award_id":"62306153,62225604","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G614977355","display_name":null,"funder_award_id":"070-63243143","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"pre-trained":[1],"diffusion":[2,26,52,130,145],"models":[3],"are":[4],"becoming":[5],"increasingly":[6],"popular":[7],"in":[8,38,183],"solving":[9],"the":[10,34,44,49,65,70,90,94,102,108,112,123,129,140,148,154,177],"Real-World":[11],"Image":[12],"Super-Resolution":[13],"(Real-ISR)":[14],"problem":[15],"because":[16],"of":[17,25,64,77,98,105,118],"their":[18],"rich":[19],"generative":[20],"priors.":[21],"The":[22,115],"recent":[23],"development":[24],"transformer":[27],"(DiT)":[28],"has":[29],"witnessed":[30],"overwhelming":[31],"performance":[32,182],"over":[33],"traditional":[35],"UNet-based":[36],"architecture":[37],"image":[39],"generation,":[40],"which":[41,185],"also":[42],"raises":[43],"question:":[45],"Can":[46],"we":[47,59,88],"adopt":[48],"advanced":[50],"DiT-based":[51],"model":[53,73,179],"for":[54,74,101,163],"Real-ISR?":[55],"To":[56],"this":[57],"end,":[58],"propose":[60],"our":[61],"DiT4SR,":[62],"one":[63],"pioneering":[66],"works":[67],"to":[68,126,167],"tame":[69],"large-scale":[71],"DiT":[72,178],"Real-ISR.":[75],"Instead":[76],"directly":[78],"injecting":[79],"embeddings":[80,92],"extracted":[81],"from":[82],"low-resolution":[83],"(LR)":[84],"images":[85],"like":[86],"ControlNet,":[87],"integrate":[89],"LR":[91,109,124,149],"into":[93,153],"original":[95],"attention":[96],"mechanism":[97],"DiT,":[99],"allowing":[100],"bidirectional":[103],"flow":[104],"information":[106],"between":[107],"latent":[110,142,156],"and":[111],"generated":[113,141,155],"latent.":[114],"sufficient":[116],"interaction":[117],"these":[119],"two":[120],"streams":[121],"allows":[122],"stream":[125],"evolve":[127],"with":[128,139,180],"process,":[131],"producing":[132],"progressively":[133],"refined":[134],"guidance":[135,150],"that":[136],"better":[137],"aligns":[138],"at":[143],"each":[144],"step.":[146],"Additionally,":[147],"is":[151,186],"injected":[152],"via":[157],"a":[158],"cross-stream":[159],"convolution":[160],"layer,":[161],"compensating":[162],"DiT's":[164],"limited":[165],"ability":[166],"capture":[168],"local":[169],"information.":[170],"These":[171],"simple":[172],"but":[173],"effective":[174],"designs":[175],"endow":[176],"superior":[181],"Real-ISR,":[184],"demonstrated":[187],"by":[188],"extensive":[189],"experiments.":[190],"Project":[191],"Page:":[192],"https://adam-duan.github.io/projects/dit4sr/.":[193]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}