{"id":"https://openalex.org/W7129756160","doi":"https://doi.org/10.1109/icipw68931.2025.11385940","title":"Deep Sparse Prior: Enhancing Deblurring Deep Priors with Sparsity Constraints","display_name":"Deep Sparse Prior: Enhancing Deblurring Deep Priors with Sparsity Constraints","publication_year":2025,"publication_date":"2025-09-14","ids":{"openalex":"https://openalex.org/W7129756160","doi":"https://doi.org/10.1109/icipw68931.2025.11385940"},"language":null,"primary_location":{"id":"doi:10.1109/icipw68931.2025.11385940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11385940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing Workshops (ICIPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092503857","display_name":"Francisco M. Castro-Mac\u00edas","orcid":"https://orcid.org/0000-0002-9040-3641"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Francisco M. Castro-Mac\u00edas","raw_affiliation_strings":["University of Granada,Dept. of Computer Science and AI,Granada,Spain"],"affiliations":[{"raw_affiliation_string":"University of Granada,Dept. of Computer Science and AI,Granada,Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126258566","display_name":"Miguel Vega","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Miguel Vega","raw_affiliation_strings":["University of Granada,Dept. Computer Languages and Systems,Granada,Spain"],"affiliations":[{"raw_affiliation_string":"University of Granada,Dept. Computer Languages and Systems,Granada,Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126271281","display_name":"Rafael Molina","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rafael Molina","raw_affiliation_strings":["University of Granada,Dept. of Computer Science and AI,Granada,Spain"],"affiliations":[{"raw_affiliation_string":"University of Granada,Dept. of Computer Science and AI,Granada,Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092503857"],"corresponding_institution_ids":["https://openalex.org/I173304897"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75531515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"422","last_page":"427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9951000213623047,"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":0.9951000213623047,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.0008999999845400453,"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":0.0008999999845400453,"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/deblurring","display_name":"Deblurring","score":0.9214000105857849},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.9197999835014343},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5828999876976013},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5023000240325928},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.48969998955726624},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4860999882221222},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4442000091075897},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4334999918937683}],"concepts":[{"id":"https://openalex.org/C2777693668","wikidata":"https://www.wikidata.org/wiki/Q25053743","display_name":"Deblurring","level":5,"score":0.9214000105857849},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.9197999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6603999733924866},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5551000237464905},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4442000091075897},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.37040001153945923},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.352400004863739},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35120001435279846},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.33070001006126404},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.329800009727478},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2540000081062317},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icipw68931.2025.11385940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11385940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing Workshops (ICIPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4296119809150696,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1795014501","https://openalex.org/W1987075379","https://openalex.org/W1996987333","https://openalex.org/W2138204001","https://openalex.org/W2138633854","https://openalex.org/W2331376995","https://openalex.org/W2465552163","https://openalex.org/W2490662969","https://openalex.org/W2507550467","https://openalex.org/W2759428153","https://openalex.org/W2963426457","https://openalex.org/W2964013315","https://openalex.org/W2982374186","https://openalex.org/W3034724715","https://openalex.org/W4250589301","https://openalex.org/W4401749692","https://openalex.org/W4415798075"],"related_works":[],"abstract_inverted_index":{"Blind":[0],"Image":[1],"Deblurring":[2],"(BID)":[3],"aims":[4],"to":[5,67,122],"recover":[6],"a":[7,15,27,90,108],"clean":[8],"image":[9],"and":[10,115],"unknown":[11],"blur":[12],"kernel":[13],"from":[14],"single":[16],"blurry":[17],"observation.":[18],"Previous":[19],"works":[20],"have":[21,48,76],"addressed":[22],"this":[23,83],"problem":[24],"using":[25],"Maximum":[26],"Posteriori":[28],"(MAP)":[29],"frameworks":[30],"with":[31,34,111,134,144],"hand-crafted":[32],"priors,":[33],"sparsity-promoting":[35],"priors":[36,55,114,143],"yielding":[37],"some":[38],"of":[39,141,148],"the":[40,65,131,138,145,159],"best":[41],"results.":[42],"More":[43],"recently,":[44],"deep":[45,92,142],"prior-based":[46,93],"approaches":[47],"achieved":[49],"state-of-the-art":[50],"performance":[51],"by":[52,103],"implicitly":[53],"learning":[54],"through":[56],"neural":[57,135],"network":[58],"architectures.":[59],"However,":[60],"these":[61],"methods":[62],"typically":[63],"lack":[64],"ability":[66],"enforce":[68],"explicit":[69],"structural":[70],"constraints,":[71],"such":[72],"as":[73],"sparsity,":[74],"which":[75],"proven":[77],"critical":[78],"in":[79],"earlier":[80],"models.":[81,105,151],"In":[82],"work,":[84],"we":[85],"propose":[86],"Deep":[87],"Sparse":[88],"Prior,":[89],"novel":[91],"method":[94,161],"for":[95],"BID":[96],"that":[97,158],"explicitly":[98],"incorporates":[99],"sparsity":[100],"constraints":[101],"inspired":[102],"MAP-based":[104],"We":[106],"adopt":[107],"Bayesian":[109],"framework":[110],"Super":[112],"Gaussian":[113,118],"utilize":[116],"their":[117],"Scale":[119],"Mixture":[120],"representations":[121],"enable":[123],"tractable":[124],"variational":[125,132],"inference.":[126],"The":[127],"proposed":[128,160],"approach":[129],"parametrizes":[130],"distributions":[133],"networks,":[136],"combining":[137],"representational":[139],"power":[140],"regularization":[146],"benefits":[147],"classical":[149],"sparse":[150],"Experiments":[152],"on":[153],"two":[154],"bench-mark":[155],"datasets":[156],"demonstrate":[157],"achieves":[162],"competitive":[163],"or":[164],"superior":[165],"performance,":[166],"validating":[167],"its":[168],"effectiveness.":[169]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-02-18T00:00:00"}