{"id":"https://openalex.org/W7161163551","doi":"https://doi.org/10.48550/arxiv.2605.13744","title":"Aligning Network Equivariance with Data Symmetry: A Theoretical Framework and Adaptive Approach for Image Restoration","display_name":"Aligning Network Equivariance with Data Symmetry: A Theoretical Framework and Adaptive Approach for Image Restoration","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161163551","doi":"https://doi.org/10.48550/arxiv.2605.13744"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13744","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13744","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.2605.13744","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133643724","display_name":"Feiyu Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Feiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136163998","display_name":"Qi Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136100417","display_name":"Zongben Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zongben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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":[]}],"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":0.361299991607666,"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":0.361299991607666,"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":0.25760000944137573,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.1573999971151352,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/equivariant-map","display_name":"Equivariant map","score":0.8201000094413757},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4952999949455261},{"id":"https://openalex.org/keywords/symmetry","display_name":"Symmetry (geometry)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4140999913215637},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.38260000944137573},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.38260000944137573},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.3774999976158142},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3734000027179718},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.8201000094413757},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4952999949455261},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47360000014305115},{"id":"https://openalex.org/C2779886137","wikidata":"https://www.wikidata.org/wiki/Q21030012","display_name":"Symmetry (geometry)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4408999979496002},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4219000041484833},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.3774999976158142},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3734000027179718},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.2865000069141388},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C146834321","wikidata":"https://www.wikidata.org/wiki/Q2979672","display_name":"Closure (psychology)","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13744","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13744","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.2605.13744","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13744","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":[{"id":"https://metadata.un.org/sdg/11","score":0.6965699195861816,"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":{"Image":[0],"restoration":[1,122,132,155],"is":[2,157],"an":[3,71,74],"inherently":[4],"ill":[5,19],"posed":[6],"inverse":[7,123,140],"problem.":[8,124],"Equivariant":[9,205],"networks":[10],"that":[11,128,148,179,207],"embed":[12],"geometric":[13],"symmetry":[14,35,84,104,145,163,184],"priors":[15],"can":[16,134],"mitigate":[17],"this":[18,67,139],"posedness":[20],"and":[21,33,77,88,113,147,165,211,230,236,243,249],"improve":[22],"performance.":[23],"However,":[24],"current":[25],"understanding":[26],"of":[27,101,152],"the":[28,79,95,106,121,129,143,149,153,161,166,173,186,192],"relationship":[29,81],"between":[30],"network":[31],"equivariance":[32,130,150,181],"data":[34,43,63,83,162,183],"remains":[36],"largely":[37],"heuristic.":[38],"Particularly":[39],"for":[40,94,131],"real":[41],"world":[42],"with":[44,182,219],"imperfect":[45],"symmetry,":[46,56],"existing":[47],"research":[48],"lacks":[49],"a":[50,98,117,202,209],"systematic":[51],"theoretical":[52,234],"framework":[53],"to":[54,119,216],"quantify":[55],"select":[57],"transformation":[58,212],"groups,":[59],"or":[60],"evaluate":[61],"model":[62,86],"alignment.":[64],"To":[65],"bridge":[66],"gap,":[68],"we":[69,92,177,200],"conduct":[70],"analysis":[72],"from":[73,138],"optimization":[75],"perspective":[76],"formalize":[78],"intrinsic":[80],"among":[82],"priors,":[85],"equivariance,":[87],"generalization":[89],"capability.":[90],"Specifically,":[91],"propose":[93,201],"first":[96],"time":[97],"quantifiable":[99],"definition":[100],"non":[102],"strict":[103],"at":[105,254],"dataset":[107],"level":[108],"(rather":[109],"than":[110],"sample":[111],"level)":[112],"use":[114],"it":[115],"as":[116],"constraint":[118],"formulate":[120],"We":[125],"then":[126],"show":[127,237],"models":[133],"be":[135],"naturally":[136],"derived":[137],"problems":[141],"incorporated":[142],"proposed":[144],"constraints,":[146],"error":[151,164],"optimal":[154],"operator":[156],"strictly":[158],"bounded":[159],"by":[160,171,197],"discretization":[167],"mesh":[168],"size.":[169],"Furthermore,":[170],"analyzing":[172],"network's":[174],"empirical":[175],"risk,":[176],"demonstrate":[178],"aligning":[180],"optimizes":[185],"bias":[187],"variance":[188],"trade":[189],"off,":[190],"minimizing":[191],"total":[193],"expected":[194],"risk.":[195],"Guided":[196],"these":[198],"insights,":[199],"Sample":[203],"Adaptive":[204],"Network":[206],"uses":[208],"hypernetwork":[210],"learnable":[213],"equivariant":[214,245],"convolutions":[215],"dynamically":[217],"align":[218],"each":[220],"sample's":[221],"inherent":[222],"symmetry.":[223],"Extensive":[224],"experiments":[225],"on":[226],"super":[227],"resolution,":[228],"denoising,":[229],"deraining":[231],"validate":[232],"our":[233],"findings":[235],"significant":[238],"superiority":[239],"over":[240],"standard":[241],"baselines":[242],"traditional":[244],"models.":[246],"Our":[247],"code":[248],"supplementary":[250],"material":[251],"are":[252],"available":[253],"https://github.com/tanfy929/SA-Conv.":[255]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-15T00:00:00"}