{"id":"https://openalex.org/W7134922640","doi":"https://doi.org/10.1109/tpami.2026.3672465","title":"StarIR: Convolutional Image Restoration With Spatial-Frequency Fusion","display_name":"StarIR: Convolutional Image Restoration With Spatial-Frequency Fusion","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134922640","doi":"https://doi.org/10.1109/tpami.2026.3672465","pmid":"https://pubmed.ncbi.nlm.nih.gov/41805516"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3672465","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3672465","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tpami.2026.3672465","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128713391","display_name":"Yuning Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuning Cui","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1279-5539","affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060899114","display_name":"Syed Waqas Zamir","orcid":"https://orcid.org/0000-0002-7198-0187"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syed Waqas Zamir","raw_affiliation_strings":["Microsoft AI for Good Research Lab, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0002-7198-0187","affiliations":[{"raw_affiliation_string":"Microsoft AI for Good Research Lab, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128756986","display_name":"Ming-Hsuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming-Hsuan Yang","raw_affiliation_strings":["University of California at Merced, Merced, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4848-2304","affiliations":[{"raw_affiliation_string":"University of California at Merced, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128693716","display_name":"Alois Knoll","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4840-076X","affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128792157","display_name":"Fahad Shahbaz Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096345","display_name":"City University","ror":"https://ror.org/00r1j9q42","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210096345"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["MBZ University of AI, Masdar City, UAE"],"raw_orcid":"https://orcid.org/0000-0002-4263-3143","affiliations":[{"raw_affiliation_string":"MBZ University of AI, Masdar City, UAE","institution_ids":["https://openalex.org/I4210096345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128704269","display_name":"Salman Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096345","display_name":"City University","ror":"https://ror.org/00r1j9q42","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210096345"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["MBZ University of AI, Masdar City, UAE"],"raw_orcid":"https://orcid.org/0000-0002-9502-1749","affiliations":[{"raw_affiliation_string":"MBZ University of AI, Masdar City, UAE","institution_ids":["https://openalex.org/I4210096345"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9689831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"48","issue":"7","first_page":"8216","last_page":"8233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.6678000092506409,"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/T11019","display_name":"Image Enhancement Techniques","score":0.6678000092506409,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.09300000220537186,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.07100000232458115,"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/robustness","display_name":"Robustness (evolution)","score":0.652999997138977},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5928000211715698},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.553600013256073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.484499990940094},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4528000056743622},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.43220001459121704},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4104999899864197},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.40619999170303345},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3702999949455261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7315999865531921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.701200008392334},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.652999997138977},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.553600013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46790000796318054},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4528000056743622},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.31769999861717224},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C125045340","wikidata":"https://www.wikidata.org/wiki/Q6002224","display_name":"Image formation","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3672465","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3672465","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41805516","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41805516","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tpami.2026.3672465","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3672465","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Transformer":[1],"(ViT)":[2],"has":[3],"shown":[4],"impressive":[5],"performance":[6,171],"in":[7,108,189],"image":[8,178,219],"restoration":[9,179],"due":[10],"to":[11,14,56,82,151,205],"its":[12,21,29],"ability":[13,55],"capture":[15,57],"a":[16,77,90,114,147],"large":[17,78],"receptive":[18,50,79],"field.":[19],"However,":[20],"complexity":[22],"grows":[23],"quadratically":[24],"with":[25,95],"input":[26],"resolution,":[27],"limiting":[28],"applicability":[30],"for":[31],"high-resolution":[32],"images.":[33],"In":[34,200],"contrast,":[35],"Convolutional":[36],"Neural":[37],"Networks":[38],"(CNNs)":[39],"are":[40,44],"computationally":[41],"efficient":[42],"but":[43],"constrained":[45],"by":[46,146],"their":[47,54],"inherently":[48],"local":[49],"fields,":[51],"which":[52,68,122],"limit":[53],"long-range":[58],"pixel":[59],"relationships.":[60],"To":[61],"address":[62],"these":[63],"challenges,":[64],"we":[65],"propose":[66],"StarIR,":[67],"possesses":[69],"the":[70,102,109,119],"efficiency":[71],"of":[72],"CNNs":[73],"while":[74],"also":[75],"capturing":[76],"field,":[80],"similar":[81],"Transformers.":[83],"StarIR":[84,168,202],"incorporates":[85],"two":[86,190,197],"key":[87],"innovations:":[88],"1)":[89],"dual-domain":[91],"representation":[92],"learning":[93],"framework,":[94],"one":[96],"branch":[97],"processing":[98],"spatial":[99],"details":[100],"and":[101,112,139,156,193,217],"other":[103],"focusing":[104],"on":[105,161,196],"mesoscale":[106],"interactions":[107],"frequency":[110],"domain;":[111],"2)":[113],"high-dimensional":[115],"feature":[116,154],"fusion":[117],"mechanism,":[118],"Star":[120,142],"operation,":[121],"fuses":[123],"information":[124],"from":[125],"both":[126],"domains":[127],"through":[128],"element-wise":[129],"multiplication,":[130],"thereby":[131],"enhancing":[132],"representational":[133],"capacity":[134],"without":[135],"increasing":[136],"network":[137],"width":[138],"depth.":[140],"Our":[141],"operation":[143],"is":[144],"followed":[145],"channel":[148],"attention":[149],"unit":[150],"facilitate":[152],"global":[153],"modeling":[155],"enhance":[157],"channel-wise":[158],"interactions.":[159],"Building":[160],"our":[162,182],"straightforward":[163],"yet":[164],"powerful":[165],"design":[166],"principles,":[167],"achieves":[169],"state-of-the-art":[170],"across":[172],"21":[173],"datasets":[174],"covering":[175],"six":[176],"single-degradation":[177],"tasks.":[180],"Furthermore,":[181],"model":[183],"performs":[184],"favorably":[185],"against":[186],"leading":[187],"algorithms":[188],"all-in-one":[191],"settings":[192],"demonstrates":[194],"robustness":[195],"composite-degradation":[198],"datasets.":[199],"addition,":[201],"extends":[203],"well":[204],"several":[206],"domain-specific":[207],"applications,":[208],"including":[209],"ultra-high-definition":[210],"(UHD)":[211],"imaging,":[212,216],"remote":[213],"sensing,":[214],"medical":[215],"underwater":[218],"enhancement.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-03-12T00:00:00"}