{"id":"https://openalex.org/W7204944760","doi":"https://doi.org/10.48550/arxiv.2608.30782","title":"PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution","display_name":"PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204944760","doi":"https://doi.org/10.48550/arxiv.2608.30782"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.30782","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30782","pdf_url":"https://arxiv.org/pdf/2608.30782","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.30782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133103717","display_name":"Bingtian Qiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Bingtian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148921294","display_name":"Yue Shi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122168611","display_name":"Yong Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148867809","display_name":"Wenjun Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090145580","display_name":"Jiezhang Cao","orcid":"https://orcid.org/0000-0002-0050-4714","observed_orcids":["https://orcid.org/0000-0002-0050-4714"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Jiezhang","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":0.9980000257492065,"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":0.9980000257492065,"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/T11019","display_name":"Image Enhancement Techniques","score":0.0003000000142492354,"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":0.0003000000142492354,"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/knowledge-distillation","display_name":"knowledge distillation","score":0.6579999923706055},{"id":"https://openalex.org/keywords/efficient-neural-networks","display_name":"efficient neural networks","score":0.3709999918937683},{"id":"https://openalex.org/keywords/low-latency-inference","display_name":"low-latency inference","score":0.4729999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311999797821045},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.6819999814033508},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630000233650208},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5422000288963318},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4927999973297119},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4036000072956085},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.36910000443458557},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.30782","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30782","pdf_url":"https://arxiv.org/pdf/2608.30782","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2608.30782","doi":"https://doi.org/10.48550/arxiv.2608.30782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.30782","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30782","pdf_url":"https://arxiv.org/pdf/2608.30782","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7223091517","https://openalex.org/W4407185488","https://openalex.org/W7204814357","https://openalex.org/W4405355335","https://openalex.org/W7220654438","https://openalex.org/W4413581770","https://openalex.org/W7156913685","https://openalex.org/W7168418376","https://openalex.org/W4414595360","https://openalex.org/W7134257414"],"abstract_inverted_index":{"Real-world":[0],"image":[1,114],"super-resolution":[2],"(Real-ISR)":[3],"aims":[4],"to":[5,36,45,121],"preserve":[6],"structures":[7],"supported":[8],"by":[9],"the":[10,33,62,118,130,141,148],"degraded":[11,119],"observation":[12,120],"while":[13],"reconstructing":[14],"perceptually":[15],"realistic":[16],"details.":[17],"However,":[18],"existing":[19],"Real-ISR":[20,74],"methods":[21,49],"largely":[22],"optimize":[23],"fidelity":[24],"and":[25,40,61,89,169,174,192],"perceptual":[26,90,132],"quality":[27],"within":[28,155],"a":[29,78,100,122,126,151,156,183,196],"shared":[30],"network,":[31],"causing":[32],"two":[34],"objectives":[35],"interfere":[37],"throughout":[38],"training":[39],"making":[41],"their":[42,67],"balance":[43],"difficult":[44],"control.":[46],"Recent":[47],"one-step":[48,153],"reduce":[50],"sampling":[51,80],"steps,":[52],"yet":[53],"often":[54],"inherit":[55],"both":[56,172],"this":[57,95],"coupled":[58],"optimization":[59],"behavior":[60],"expensive":[63],"high-resolution":[64],"backbone":[65],"of":[66,86],"multi-step":[68],"predecessors.":[69],"We":[70,145],"argue":[71],"that":[72,116,163],"efficient":[73],"requires":[75],"not":[76],"only":[77,187],"shorter":[79],"trajectory,":[81],"but":[82],"also":[83],"specialized":[84],"modeling":[85],"faithful":[87,123],"reconstruction":[88],"detail":[91],"synthesis.":[92],"Based":[93],"on":[94,171],"insight,":[96],"we":[97],"propose":[98],"PixelIR,":[99],"fidelity-perception":[101],"decoupling":[102],"framework":[103],"built":[104],"upon":[105],"pixel-space":[106,180],"image-residual":[107],"flow":[108,115,128],"matching.":[109],"PixelIR":[110,164],"first":[111],"learns":[112],"an":[113],"maps":[117],"reconstruction.":[124],"Then,":[125],"residual":[127],"synthesizes":[129],"missing":[131],"details":[133],"from":[134],"noise":[135],"without":[136],"repeatedly":[137],"relearning":[138],"or":[139],"overwriting":[140],"complete":[142],"restoration":[143,181],"solution.":[144],"further":[146],"distill":[147],"teacher":[149],"into":[150],"deployment-oriented":[152],"student":[154],"coarse-to-fine":[157],"pyramid":[158],"architecture.":[159],"Extensive":[160],"experiments":[161],"show":[162],"achieves":[165],"leading":[166],"PSNR,":[167],"SSIM,":[168],"LPIPS":[170],"RealSR":[173],"DRealSR.":[175],"The":[176],"final":[177],"model":[178],"completes":[179],"in":[182],"single":[184],"evaluation":[185],"with":[186],"32.9M":[188],"parameters,":[189],"89.7G":[190],"MACs,":[191],"8.5ms":[193],"latency,":[194],"demonstrating":[195],"strong":[197],"practical":[198],"fidelity-perception-efficiency":[199],"balance.":[200]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-02T00:00:00"}