{"id":"https://openalex.org/W3011455794","doi":"https://doi.org/10.1109/tmm.2020.2981185","title":"Fast Non-Local Adaptive In-Loop Filter Optimization on GPU","display_name":"Fast Non-Local Adaptive In-Loop Filter Optimization on GPU","publication_year":2020,"publication_date":"2020-03-18","ids":{"openalex":"https://openalex.org/W3011455794","doi":"https://doi.org/10.1109/tmm.2020.2981185","mag":"3011455794"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2020.2981185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2981185","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","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/A5040292663","display_name":"Chuanmin Jia","orcid":"https://orcid.org/0000-0002-7418-6245"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanmin Jia","raw_affiliation_strings":["Institute of Digital Media, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7418-6245","affiliations":[{"raw_affiliation_string":"Institute of Digital Media, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086988634","display_name":"Falei Luo","orcid":"https://orcid.org/0000-0003-3263-9549"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Falei Luo","raw_affiliation_strings":["Institute of Digital Media, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3263-9549","affiliations":[{"raw_affiliation_string":"Institute of Digital Media, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055937409","display_name":"Xinfeng Zhang","orcid":"https://orcid.org/0000-0002-7517-3868"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfeng Zhang","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7517-3868","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385178","display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0002-3583-959X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kwoloon, Hong Kong","Institute of Digital Media, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3583-959X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kwoloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Institute of Digital Media, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385183","display_name":"Shanshe Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Shanshe Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kwoloon, Hong Kong","Institute of Digital Media, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7665-7434","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kwoloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Institute of Digital Media, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039832462","display_name":"Siwei Ma","orcid":"https://orcid.org/0000-0002-2731-5403"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siwei Ma","raw_affiliation_strings":["Institute of Digital Media, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2731-5403","affiliations":[{"raw_affiliation_string":"Institute of Digital Media, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9124,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7321941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"23","issue":null,"first_page":"39","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9993000030517578,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9993000030517578,"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":0.9254783391952515},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.600415825843811},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5486028790473938},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4767744839191437},{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.4528660178184509},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.444894939661026},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36950838565826416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9254783391952515},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.600415825843811},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5486028790473938},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4767744839191437},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.4528660178184509},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.444894939661026},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36950838565826416},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2020.2981185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.2981185","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1964952269","https://openalex.org/W1982999867","https://openalex.org/W1984222112","https://openalex.org/W2004025832","https://openalex.org/W2016939324","https://openalex.org/W2017801928","https://openalex.org/W2046742427","https://openalex.org/W2056061164","https://openalex.org/W2057049255","https://openalex.org/W2064674198","https://openalex.org/W2075984142","https://openalex.org/W2098395302","https://openalex.org/W2121397913","https://openalex.org/W2122006312","https://openalex.org/W2122086266","https://openalex.org/W2123113293","https://openalex.org/W2136604529","https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2152029399","https://openalex.org/W2155893237","https://openalex.org/W2382163890","https://openalex.org/W2402144811","https://openalex.org/W2428965074","https://openalex.org/W2546648313","https://openalex.org/W2561375249","https://openalex.org/W2610472635","https://openalex.org/W2757350145","https://openalex.org/W2789951514","https://openalex.org/W2889064837","https://openalex.org/W2891220565","https://openalex.org/W2913664580","https://openalex.org/W2953384591","https://openalex.org/W3041093287","https://openalex.org/W3104540617","https://openalex.org/W6664967405","https://openalex.org/W6675084218","https://openalex.org/W6680611266","https://openalex.org/W6713134421","https://openalex.org/W6717810278"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2983282793","https://openalex.org/W2042531701","https://openalex.org/W2953286784","https://openalex.org/W1488921751","https://openalex.org/W2122729175"],"abstract_inverted_index":{"The":[0,116],"non-local":[1,17],"adaptive":[2],"in-loop":[3],"filter":[4],"(NALF)":[5],"for":[6,121],"video":[7,37,190],"coding":[8,12,176,191],"has":[9],"achieved":[10],"significant":[11,175],"gain":[13],"by":[14,52,96,146],"exploiting":[15],"image":[16],"self-similarity":[18],"(NSS)":[19],"to":[20,80,82,100,112],"efficiently":[21],"reduce":[22,132],"the":[23,27,54,62,73,83,94,102,108,133,138,148,161,174,183,188],"compression":[24],"artifacts.":[25],"However,":[26],"intensive":[28],"computation":[29],"of":[30,59,65,75,150,178,185],"NALF":[31,46,67,95,164,186],"hinders":[32],"its":[33],"practical":[34],"deployment":[35],"in":[36,49,70,135,154,187],"standardizations.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,91],"propose":[43],"a":[44],"fast":[45,163],"optimization":[47,165],"algorithm":[48],"parallel-computing":[50],"framework":[51],"leveraging":[53],"massive":[55],"parallel":[56],"execution":[57],"resources":[58],"GPU.":[60],"First,":[61],"computational":[63],"complexity":[64],"original":[66,179],"is":[68,142],"analyzed":[69],"depth,":[71],"then":[72],"pipelines":[74],"computational-intensive":[76],"modules":[77,127],"are":[78,128],"re-designed":[79],"adapt":[81],"general-purpose":[84],"GPU":[85,109,145,167],"with":[86],"more":[87],"parallel-friendly":[88],"consideration.":[89],"Specifically,":[90],"speed":[92],"up":[93],"optimizing":[97],"thread":[98],"allocation":[99],"maximize":[101],"parallelism":[103],"degree":[104],"and":[105,118,124],"elaborately":[106],"designing":[107],"block":[110],"dimension":[111],"avoid":[113],"access":[114],"conflict.":[115],"group-level":[117],"pixel-level":[119],"parallelization":[120],"collaboratively":[122],"filtering":[123,140],"patch":[125],"matching":[126],"designed":[129],"respectively.":[130],"To":[131],"cost":[134],"data":[136,152],"transmission,":[137],"whole":[139],"process":[141],"implemented":[143],"on":[144],"taking":[147],"advantage":[149],"low":[151],"dependency":[153],"NALF.":[155],"Extensive":[156],"experimental":[157],"results":[158],"show":[159],"that":[160],"proposed":[162],"using":[166],"architecture":[168],"achieves":[169],"high-speeed":[170],"processing":[171],"while":[172],"maintaining":[173],"performance":[177],"NALF,":[180],"which":[181],"shows":[182],"potential":[184],"future":[189],"standard.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}