{"id":"https://openalex.org/W7164891270","doi":"https://doi.org/10.48550/arxiv.2606.16188","title":"teasr: training-efficient any-step diffusion transformer for real-world image super-resolution","display_name":"teasr: training-efficient any-step diffusion transformer for real-world image super-resolution","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164891270","doi":"https://doi.org/10.48550/arxiv.2606.16188"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.16188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16188","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.16188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103668258","display_name":"Gao X","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132685613","display_name":"Chenxin Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Chenxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103512462","display_name":"Y D Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Yushun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138716529","display_name":"Qiang Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138707869","display_name":"Xiaoyun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaoyun","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":0,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.8726999759674072,"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":0.8726999759674072,"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":0.048700001090765,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.010999999940395355,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5194000005722046},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47589999437332153},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.4699000120162964},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.45879998803138733},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4422000050544739},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4262000024318695},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4187999963760376},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3971000015735626},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.3716999888420105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682000160217285},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5194000005722046},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47589999437332153},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.4699000120162964},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4187999963760376},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3741999864578247},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3716999888420105},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36489999294281006},{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.3447999954223633},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.3271999955177307},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.32179999351501465},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2653999924659729}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.16188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16188","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":"doi:10.48550/arxiv.2606.16188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16188","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6433975100517273,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1,32,46,125],"excel":[2],"in":[3],"Real-World":[4],"Image":[5],"Super-Resolution":[6],"(Real-ISR)":[7],"due":[8],"to":[9,40,50,84,145,155],"their":[10],"powerful":[11],"generative":[12],"priors":[13],"but":[14],"suffer":[15],"from":[16],"slow":[17],"iterative":[18],"sampling.":[19],"Although":[20],"existing":[21],"one-step":[22,72,110],"distillation":[23,87,121],"methods":[24,172],"accelerate":[25],"inference,":[26],"they":[27],"typically":[28],"require":[29],"auxiliary":[30,97],"teacher":[31],"that":[33,69,108,162],"inflate":[34],"training":[35,132],"memory":[36],"and":[37,73,151,168],"restrict":[38],"scalability":[39],"large-scale":[41],"architectures.":[42],"Furthermore,":[43],"these":[44],"fixed-step":[45],"lack":[47],"the":[48,94,120,147,152],"flexibility":[49],"trade":[51],"off":[52],"speed":[53],"for":[54,67,96],"quality.":[55,158],"In":[56],"this":[57],"paper,":[58],"we":[59,102,135],"propose":[60,103],"TEASR,":[61],"a":[62,77,89,104,127,137],"training-efficient":[63],"any-step":[64,166],"diffusion":[65,91,124,139],"framework":[66],"Real-ISR":[68],"enables":[70,119],"both":[71],"multi-step":[74],"restoration":[75],"within":[76,88],"unified":[78],"model.":[79],"Our":[80],"key":[81],"idea":[82],"is":[83],"perform":[85],"self-adversarial":[86],"single":[90,128],"model,":[92],"eliminating":[93],"need":[95],"teachers":[98],"or":[99],"discriminators.":[100],"Specifically,":[101],"timestep-aware":[105],"rectification":[106],"strategy":[107],"stabilizes":[109],"generation":[111],"across":[112,173],"noise":[113,149],"levels.":[114],"These":[115],"two":[116],"designs":[117],"further":[118],"of":[122],"20B-parameter":[123],"on":[126],"GPU,":[129],"significantly":[130],"improving":[131],"efficiency.":[133],"Moreover,":[134],"introduce":[136],"dual-branch":[138],"transformer":[140],"with":[141],"decoupled":[142],"timestep":[143],"condition":[144],"separate":[146],"current":[148],"state":[150],"denoising":[153],"target":[154],"enhance":[156],"sampling":[157,167],"Extensive":[159],"experiments":[160],"demonstrate":[161],"TEASR":[163],"supports":[164],"seamless":[165],"consistently":[169],"outperforms":[170],"state-of-the-art":[171],"multiple":[174],"datasets.":[175]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}