{"id":"https://openalex.org/W7161180951","doi":"https://doi.org/10.48550/arxiv.2605.13581","title":"HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation","display_name":"HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161180951","doi":"https://doi.org/10.48550/arxiv.2605.13581"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13581","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.2605.13581","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136091467","display_name":"Li Pang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pang, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136182753","display_name":"Heng Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Heng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129745825","display_name":"Yijia Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yijia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136116724","display_name":"Deyu Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Deyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028103486","display_name":"Xiangyong Cao","orcid":"https://orcid.org/0000-0001-7912-3457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Xiangyong","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/T10688","display_name":"Image and Signal Denoising Methods","score":0.4106000065803528,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.4106000065803528,"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":0.2619999945163727,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.15569999814033508,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperspectral-imaging","display_name":"Hyperspectral imaging","score":0.8808000087738037},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.6083999872207642},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4722999930381775},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4117000102996826},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.39750000834465027},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.36980000138282776},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.351500004529953}],"concepts":[{"id":"https://openalex.org/C159078339","wikidata":"https://www.wikidata.org/wiki/Q959005","display_name":"Hyperspectral imaging","level":2,"score":0.8808000087738037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6384000182151794},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.6083999872207642},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4277999997138977},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3476000130176544},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C141239990","wikidata":"https://www.wikidata.org/wiki/Q957423","display_name":"Superresolution","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13581","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.2605.13581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13581","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":[{"score":0.6013771891593933,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hyperspectral":[0],"image":[1],"(HSI)":[2],"restoration":[3,52,80,161,224],"is":[4,229],"crucial":[5],"for":[6],"reliable":[7],"analysis,":[8],"as":[9],"real-world":[10,36],"HSIs":[11,92,127,172],"suffer":[12],"from":[13,110],"noise,":[14],"blur,":[15],"and":[16,116,142,146,155,173,209,216,222,235],"resolution":[17],"loss.":[18],"However,":[19],"existing":[20],"models":[21,81],"trained":[22],"on":[23,28,164,179,214],"source":[24,166],"data":[25,60],"often":[26],"fail":[27],"target":[29,63,86,181],"domains":[30],"lacking":[31],"clean":[32,67,95],"references,":[33],"a":[34,44,102,198],"common":[35],"scenario.":[37],"To":[38],"address":[39],"this,":[40],"we":[41],"present":[42],"HIR-ALIGN,":[43],"plug-and-play":[45],"target-adaptive":[46],"augmentation":[47],"framework":[48],"that":[49,93,227],"enhances":[50],"HSI":[51,69],"by":[53,128,204],"augmenting":[54],"limited":[55],"training":[56],"images":[57],"with":[58,113,133,170],"synthetic":[59],"matching":[61],"the":[62,152,165,193],"distribution,":[64],"without":[65],"extra":[66],"target-domain":[68,96,200],"data.":[70],"It":[71],"has":[72],"three":[73],"stages:":[74],"(i)":[75],"proxy":[76,91,111,135,153,171],"generation,":[77],"where":[78,101,160],"off-the-shelf":[79],"are":[82,168],"applied":[83],"to":[84,88,151,231],"degraded":[85,180],"observations":[87],"produce":[89],"semantics-preserving":[90],"approximate":[94],"images;":[97],"(ii)":[98],"distribution-adaptive":[99],"synthesis,":[100],"blur-robust":[103],"unCLIP":[104],"diffusion":[105],"model":[106],"generates":[107],"target-aligned":[108,175],"RGBs":[109,112],"prompt":[114],"conditioning":[115],"embedding-space":[117],"noise":[118],"initialization.":[119],"The":[120],"warp-based":[121],"spectral":[122,211],"transfer":[123],"module":[124],"then":[125,177],"synthesizes":[126],"aligning":[129],"each":[130],"generated":[131],"RGB":[132],"its":[134],"RGB,":[136],"estimating":[137],"soft":[138],"patch-wise":[139],"transport":[140],"weights,":[141],"applying":[143],"these":[144],"weights":[145],"learnable":[147],"local":[148],"interpolation":[149],"kernels":[150],"HSI;":[154],"(iii)":[156],"aligned":[157],"supervised":[158],"finetuning,":[159],"networks":[162],"pretrained":[163],"distribution":[167],"finetuned":[169],"synthesized":[174],"HSIs,":[176],"deployed":[178],"images.":[182],"We":[183],"also":[184],"provide":[185],"theoretical":[186],"analysis":[187],"showing":[188],"that,":[189],"under":[190],"stated":[191],"assumptions,":[192],"proposed":[194],"augmentation-based":[195],"finetuning":[196],"obtains":[197],"tighter":[199],"restoration-risk":[201],"upper":[202],"bound":[203],"jointly":[205],"improving":[206],"target-distribution":[207],"coverage":[208],"controlling":[210],"bias.":[212],"Experiments":[213],"simulated":[215],"real":[217],"datasets":[218],"across":[219],"denoising,":[220],"super-resolution,":[221],"other":[223],"tasks":[225],"demonstrate":[226],"HIR-ALIGN":[228],"superior":[230],"proxy-only":[232],"target-adaptation":[233],"baselines":[234],"outperforms":[236],"representative":[237],"unsupervised":[238],"methods":[239],"in":[240],"most":[241],"cases.":[242]},"counts_by_year":[],"updated_date":"2026-07-03T06:15:21.484131","created_date":"2026-05-15T00:00:00"}