{"id":"https://openalex.org/W4416214937","doi":"https://doi.org/10.1109/jstsp.2025.3632532","title":"Deep Equilibrium Model With Weighted Densely-Connected Iteration Differences for Convergent Image Restoration","display_name":"Deep Equilibrium Model With Weighted Densely-Connected Iteration Differences for Convergent Image Restoration","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416214937","doi":"https://doi.org/10.1109/jstsp.2025.3632532"},"language":null,"primary_location":{"id":"doi:10.1109/jstsp.2025.3632532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3632532","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5073652872","display_name":"Ziyang Zheng","orcid":"https://orcid.org/0000-0001-9923-8016"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9923-8016","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045342512","display_name":"Wenrui Dai","orcid":"https://orcid.org/0000-0003-2522-5778"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Dai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2522-5778","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066789410","display_name":"Jingwei Liang","orcid":"https://orcid.org/0000-0003-0752-3851"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Liang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0752-3851","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113113919","display_name":"Xinyu Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Peng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086442836","display_name":"Duoduo Xue","orcid":"https://orcid.org/0000-0002-6608-5700"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duoduo Xue","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6608-5700","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Xiong","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4552-0029","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30904685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"8","first_page":"1873","last_page":"1889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.6435999870300293,"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":0.6435999870300293,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12409999966621399,"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":0.04450000077486038,"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/convergence","display_name":"Convergence (economics)","score":0.5989000201225281},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.559499979019165},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5325000286102295},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.4796999990940094},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46720001101493835},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4569000005722046},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.450300008058548},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4415000081062317},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.42480000853538513}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5600000023841858},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5325000286102295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5220000147819519},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5026999711990356},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.4796999990940094},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3571999967098236},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32659998536109924},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.31769999861717224},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C116149140","wikidata":"https://www.wikidata.org/wiki/Q2070951","display_name":"Descent direction","level":4,"score":0.2930999994277954},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2025.3632532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3632532","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1080903817","display_name":null,"funder_award_id":"62320106003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1206496187","display_name":null,"funder_award_id":"62401367","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2048617456","display_name":null,"funder_award_id":"62301299","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2895017225","display_name":null,"funder_award_id":"U24A20251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G376436071","display_name":null,"funder_award_id":"62401357","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6094063813","display_name":null,"funder_award_id":"62125109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6263369104","display_name":null,"funder_award_id":"62431017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6308568386","display_name":null,"funder_award_id":"62401366","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7123918047","display_name":null,"funder_award_id":"62120106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7931220373","display_name":null,"funder_award_id":"62371288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1967138577","https://openalex.org/W1977822596","https://openalex.org/W2004160833","https://openalex.org/W2021361347","https://openalex.org/W2022541060","https://openalex.org/W2038281434","https://openalex.org/W2087416986","https://openalex.org/W2100556411","https://openalex.org/W2194775991","https://openalex.org/W2331639718","https://openalex.org/W2613155248","https://openalex.org/W2768814045","https://openalex.org/W2798559986","https://openalex.org/W2901838001","https://openalex.org/W2902719825","https://openalex.org/W2963446712","https://openalex.org/W2963725279","https://openalex.org/W2997680707","https://openalex.org/W3000775737","https://openalex.org/W3167568784","https://openalex.org/W3180322328","https://openalex.org/W3204483762","https://openalex.org/W3206211787","https://openalex.org/W3206437644","https://openalex.org/W3207346178","https://openalex.org/W3207918547","https://openalex.org/W3210579285","https://openalex.org/W4224948589","https://openalex.org/W4249736682","https://openalex.org/W4281980169","https://openalex.org/W4292363360","https://openalex.org/W4321483944","https://openalex.org/W4323338375","https://openalex.org/W4324291866","https://openalex.org/W4372266722","https://openalex.org/W4372266829","https://openalex.org/W4382240110","https://openalex.org/W4384519135","https://openalex.org/W4385453273","https://openalex.org/W4385804996","https://openalex.org/W4386071946","https://openalex.org/W4399589032","https://openalex.org/W4402716282","https://openalex.org/W4403792434","https://openalex.org/W4413155725"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"equilibrium":[1],"models":[2],"(DEMs)":[3],"are":[4,35],"emerging":[5],"as":[6,144],"an":[7],"efficient":[8],"alternative":[9],"to":[10,37,43,65,113,135,148,182],"train":[11],"deep":[12,91],"unrolling":[13],"networks":[14],"(DUNs)":[15],"realized":[16],"by":[17],"recasting":[18],"iterative":[19],"optimization":[20,87],"algorithms":[21],"for":[22,49,117,154,166,169,220,224],"image":[23,199],"restoration":[24],"(IR)":[25],"in":[26,55,173],"a":[27,84,90,101,145,183,193,217],"single":[28],"iteration":[29,111,124],"using":[30],"constant":[31],"memory":[32],"usage":[33],"and":[34,59,70,96,132,139,175,202],"potential":[36],"allow":[38],"infinite":[39],"iterations":[40,64,128],"until":[41],"convergence":[42,76],"fixed":[44],"points.":[45],"However,":[46],"existing":[47],"DEMs":[48],"IR":[50,86,225],"suffer":[51],"from":[52,126],"architectural":[53],"constraints":[54],"exploiting":[56],"skip":[57],"connections":[58],"adaptive":[60,130],"parameters":[61],"varying":[62],"with":[63,74,89,108,129,190,213],"simultaneously":[66],"benefit":[67],"feature":[68,137],"learning":[69],"achieve":[71],"stable":[72],"reconstruction":[73,211],"theoretical":[75,167],"guarantees.":[77],"To":[78],"address":[79],"these":[80],"challenges,":[81],"we":[82,120,157],"formulate":[83],"novel":[85],"problem":[88,147],"neural":[92],"network":[93],"(DNN)-based":[94],"energy":[95,172],"propose":[97],"<italic":[98,178,206],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[99,179,207],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">DenseDiff</i>,":[100],"DEM":[102],"based":[103],"on":[104,198],"proximal":[105],"gradient":[106],"descent":[107],"weighted":[109],"densely-connected":[110],"differences,":[112],"solve":[114],"it.":[115],"Specifically,":[116],"each":[118],"iteration,":[119],"combine":[121],"densely":[122],"connected":[123],"differences":[125],"preceding":[127],"weights":[131],"step":[133],"sizes":[134],"facilitate":[136],"learning,":[138],"reformulate":[140],"multi-variable":[141],"fixed-point":[142],"computation":[143],"two-variable":[146],"preserve":[149],"the":[150,160,171,187],"effective":[151],"parameter":[152],"space":[153],"optimization.":[155],"Furthermore,":[156],"thoroughly":[158],"explore":[159],"properties":[161],"of":[162,186],"common":[163],"DNN":[164],"components":[165],"guidance":[168],"constituting":[170],"practice,":[174],"demonstrate":[176],"that":[177,205],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">DenseDiff</i>":[180,208],"converges":[181],"critical":[184],"point":[185],"objective":[188],"function":[189],"at":[191],"least":[192],"sublinear":[194],"rate.":[195],"Comprehensive":[196],"evaluations":[197],"deblurring,":[200],"inpainting,":[201],"CS-MRI":[203],"reveal":[204],"achieves":[209],"state-of-the-art":[210],"performance":[212],"guaranteed":[214],"convergence,":[215],"suggesting":[216],"promising":[218],"paradigm":[219],"designing":[221],"interpretable":[222],"DNNs":[223],"tasks.":[226]},"counts_by_year":[],"updated_date":"2026-02-09T05:59:30.833894","created_date":"2025-11-14T00:00:00"}