{"id":"https://openalex.org/W7133335189","doi":"https://doi.org/10.48550/arxiv.2603.00853","title":"Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement","display_name":"Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement","publication_year":2026,"publication_date":"2026-03-01","ids":{"openalex":"https://openalex.org/W7133335189","doi":"https://doi.org/10.48550/arxiv.2603.00853"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00853","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00853","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128010604","display_name":"Cong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Cong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113181511","display_name":"jinshan pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Jinshan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127894794","display_name":"Liyan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Liyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127914829","display_name":"Wei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128022487","display_name":"Yang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5128010604"],"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":0.8295999765396118,"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":0.8295999765396118,"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":0.1088000014424324,"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/T11897","display_name":"Digital Holography and Microscopy","score":0.015799999237060547,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"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/image-restoration","display_name":"Image restoration","score":0.7806000113487244},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5950000286102295},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.536300003528595},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5141000151634216},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.4397999942302704},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4235999882221222},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.3610999882221222}],"concepts":[{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.7806000113487244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779000163078308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6679999828338623},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5950000286102295},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5141000151634216},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5004000067710876},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.4397999942302704},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00853","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00853","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6435830593109131,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1,118],"a":[2,7,95,119],"simple":[3],"yet":[4],"effective":[5],"UHDPromer,":[6],"neural":[8,30],"discrimination-prompted":[9],"Transformer,":[10],"for":[11],"Ultra-High-Definition":[12],"(UHD)":[13],"image":[14,134,153,160,162,165],"restoration":[15,154],"and":[16,34,37,60,71,155,164,170],"enhancement.":[17],"Our":[18],"UHDPromer":[19,139],"is":[20,124],"inspired":[21],"by":[22,82,100,126],"an":[23],"interesting":[24],"observation":[25],"that":[26,138],"there":[27],"implicitly":[28],"exist":[29],"differences":[31,40,59],"between":[32],"high-resolution":[33],"low-resolution":[35,43,128],"features,":[36],"exploring":[38],"such":[39],"can":[41],"facilitate":[42,131],"feature":[44],"representation.":[45],"To":[46,110],"this":[47],"end,":[48],"we":[49,117],"first":[50],"introduce":[51],"Neural":[52,67,72],"Discrimination":[53],"Priors":[54],"(NDP)":[55],"to":[56,85,102,130],"measure":[57],"the":[58,65,80,92,105,112,141],"then":[61],"integrate":[62],"NDP":[63,84,101],"into":[64],"proposed":[66,77],"Discrimination-Prompted":[68,73],"Attention":[69],"(NDPA)":[70],"Network":[74],"(NDPN).":[75],"The":[76,167],"NDPA":[78],"re-formulates":[79],"attention":[81],"incorporating":[83],"globally":[86],"perceive":[87],"useful":[88],"discrimination":[89],"information,":[90],"while":[91,145],"NDPN":[93],"explores":[94],"continuous":[96],"gating":[97],"mechanism":[98],"guided":[99,125],"selectively":[103],"permit":[104],"passage":[106],"of":[107,114],"beneficial":[108],"content.":[109],"enhance":[111],"quality":[113],"restored":[115],"images,":[116],"super-resolution-guided":[120],"reconstruction":[121],"approach,":[122],"which":[123],"super-resolving":[127],"features":[129],"final":[132],"UHD":[133,152],"restoration.":[135],"Experiments":[136],"show":[137],"achieves":[140],"best":[142],"computational":[143],"efficiency":[144],"still":[146],"maintaining":[147],"state-of-the-art":[148],"performance":[149],"on":[150],"$3$":[151],"enhancement":[156],"tasks,":[157],"including":[158],"low-light":[159],"enhancement,":[161],"dehazing,":[163],"deblurring.":[166],"source":[168],"codes":[169],"pre-trained":[171],"models":[172],"will":[173],"be":[174],"made":[175],"available":[176],"at":[177],"https://github.com/supersupercong/uhdpromer.":[178]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}