{"id":"https://openalex.org/W3015558387","doi":"https://doi.org/10.1109/icassp40776.2020.9054201","title":"Graph Neural Net Using Analytical Graph Filters and Topology Optimization for Image Denoising","display_name":"Graph Neural Net Using Analytical Graph Filters and Topology Optimization for Image Denoising","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015558387","doi":"https://doi.org/10.1109/icassp40776.2020.9054201","mag":"3015558387"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039419978","display_name":"Weng-Tai Su","orcid":"https://orcid.org/0000-0003-3230-6760"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Weng-tai Su","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038897476","display_name":"Gene Cheung","orcid":"https://orcid.org/0000-0002-5571-4137"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gene Cheung","raw_affiliation_strings":["Department of Electrical Engineering & Computer Science, York University, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering & Computer Science, York University, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089232277","display_name":"Richard P. Wildes","orcid":"https://orcid.org/0000-0003-3433-1329"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard Wildes","raw_affiliation_strings":["Department of Electrical Engineering & Computer Science, York University, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering & Computer Science, York University, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051264473","display_name":"Chia\u2010Wen Lin","orcid":"https://orcid.org/0000-0002-9097-2318"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Wen Lin","raw_affiliation_strings":["Department of Electrical Engineering, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039419978"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":1.0564,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71670092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8464","last_page":"8468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.648556113243103},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6466025114059448},{"id":"https://openalex.org/keywords/biorthogonal-system","display_name":"Biorthogonal system","score":0.6009723544120789},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6008810997009277},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5846281051635742},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5640578866004944},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.49626070261001587},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4932803511619568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.426556259393692},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.37374991178512573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2896220088005066},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2766033411026001},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.14103341102600098},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0756470263004303},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.07376605272293091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.648556113243103},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6466025114059448},{"id":"https://openalex.org/C158453530","wikidata":"https://www.wikidata.org/wiki/Q864692","display_name":"Biorthogonal system","level":4,"score":0.6009723544120789},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6008810997009277},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5846281051635742},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5640578866004944},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.49626070261001587},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4932803511619568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.426556259393692},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.37374991178512573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2896220088005066},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2766033411026001},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.14103341102600098},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0756470263004303},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.07376605272293091},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W54257720","https://openalex.org/W1511572470","https://openalex.org/W1890834058","https://openalex.org/W1901129140","https://openalex.org/W1970352604","https://openalex.org/W1998419211","https://openalex.org/W2024496749","https://openalex.org/W2043382734","https://openalex.org/W2048695508","https://openalex.org/W2056370875","https://openalex.org/W2099244020","https://openalex.org/W2105884433","https://openalex.org/W2116857329","https://openalex.org/W2125527601","https://openalex.org/W2153663612","https://openalex.org/W2163605009","https://openalex.org/W2166235716","https://openalex.org/W2194775991","https://openalex.org/W2242218935","https://openalex.org/W2247823745","https://openalex.org/W2296399167","https://openalex.org/W2508457857","https://openalex.org/W2571662414","https://openalex.org/W2739744923","https://openalex.org/W2796431263","https://openalex.org/W2963366932","https://openalex.org/W2963972490","https://openalex.org/W2964030969","https://openalex.org/W2964228184","https://openalex.org/W2967023393","https://openalex.org/W4230938240","https://openalex.org/W6602211262","https://openalex.org/W6639824700","https://openalex.org/W6662532501","https://openalex.org/W6684191040","https://openalex.org/W6690498163","https://openalex.org/W6748551697"],"related_works":["https://openalex.org/W2002704363","https://openalex.org/W2377588290","https://openalex.org/W2326317736","https://openalex.org/W2389135727","https://openalex.org/W1967763791","https://openalex.org/W2058719641","https://openalex.org/W1496843484","https://openalex.org/W2373313192","https://openalex.org/W1979714115","https://openalex.org/W2073374589"],"abstract_inverted_index":{"While":[0],"convolutional":[1,60],"neural":[2,50],"nets":[3],"(CNNs)":[4],"have":[5],"achieved":[6],"remarkable":[7],"performance":[8,137],"for":[9],"a":[10,23,46,140],"wide":[11],"range":[12],"of":[13,84],"inverse":[14],"imaging":[15],"applications,":[16],"the":[17,78,115,145,151],"filter":[18,101],"coefficients":[19],"are":[20,28],"computed":[21],"in":[22,41,62,167],"purely":[24],"data-driven":[25],"manner":[26],"and":[27,71,75,147,154],"not":[29],"explainable.":[30],"Inspired":[31],"by":[32,37,163],"an":[33,125],"analytically":[34,69],"derived":[35],"CNN":[36],"Hadji":[38],"et":[39],"al.,":[40],"this":[42],"paper":[43],"we":[44,76,128],"construct":[45],"new":[47],"layered":[48],"graph":[49,57,86,100,116],"net":[51],"(GNN)":[52],"using":[53],"GraphBio":[54,67],"as":[55,108],"our":[56,65,98,131,158],"filter.":[58],"Unlike":[59],"filters":[61],"previous":[63],"GNNs,":[64],"employed":[66],"is":[68,105,119],"defined":[70],"requires":[72],"no":[73],"training,":[74],"optimize":[77],"end-to-end":[79],"system":[80],"only":[81],"via":[82,121],"learning":[83],"appropriate":[85],"topology":[87],"at":[88,102],"each":[89,103],"layer.":[90],"In":[91],"signal":[92],"filtering":[93],"terms,":[94],"it":[95,162],"means":[96],"that":[97,130],"linear":[99],"layer":[104],"always":[106],"intrepretable":[107],"low-pass":[109],"with":[110],"known":[111],"biorthogonal":[112],"conditions,":[113],"while":[114],"spectrum":[117],"itself":[118],"optimized":[120],"data":[122,149],"training.":[123],"As":[124],"example":[126],"application,":[127],"show":[129],"analytical":[132,159],"GNN":[133,160],"achieves":[134],"image":[135],"denoising":[136],"comparable":[138],"to":[139],"state-of-the-art":[141],"CNN-based":[142],"scheme":[143],"when":[144,155],"training":[146],"testing":[148],"share":[150],"same":[152],"statistics,":[153],"they":[156],"differ,":[157],"outperforms":[161],"more":[164],"than":[165],"1dB":[166],"PSNR.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}