{"id":"https://openalex.org/W4416961008","doi":"https://doi.org/10.1109/tbc.2025.3635389","title":"SFTNet: Spatial-Frequency Transformer Network for Learned Image Compression","display_name":"SFTNet: Spatial-Frequency Transformer Network for Learned Image Compression","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416961008","doi":"https://doi.org/10.1109/tbc.2025.3635389"},"language":null,"primary_location":{"id":"doi:10.1109/tbc.2025.3635389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbc.2025.3635389","pdf_url":null,"source":{"id":"https://openalex.org/S100142436","display_name":"IEEE Transactions on Broadcasting","issn_l":"0018-9316","issn":["0018-9316","1557-9611"],"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 Broadcasting","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/A5101628778","display_name":"Meiqin Liu","orcid":"https://orcid.org/0000-0001-8428-5098"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiqin Liu","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8428-5098","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lingxue Li","orcid":"https://orcid.org/0009-0007-9310-8756"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxue Li","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-9310-8756","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106944897","display_name":"J.H. Liang","orcid":"https://orcid.org/0009-0005-0542-7761"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Liang","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-0542-7761","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678298","display_name":"Chao Yao","orcid":"https://orcid.org/0000-0001-5483-3225"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yao","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5483-3225","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678706","display_name":"Jian Jin","orcid":"https://orcid.org/0000-0003-4250-1519"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jian Jin","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4250-1519","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060448106","display_name":"Tammam Tillo","orcid":"https://orcid.org/0000-0002-5782-644X"},"institutions":[{"id":"https://openalex.org/I46305995","display_name":"Taiyuan University of Science and Technology","ror":"https://ror.org/01wcbdc92","country_code":"CN","type":"education","lineage":["https://openalex.org/I46305995"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tammam Tillo","raw_affiliation_strings":["Institute of Digital Media and Communication, Taiyuan University of Science and Technology, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0002-5782-644X","affiliations":[{"raw_affiliation_string":"Institute of Digital Media and Communication, Taiyuan University of Science and Technology, Taiyuan, China","institution_ids":["https://openalex.org/I46305995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362745","display_name":"Yao Zhao","orcid":"https://orcid.org/0000-0002-8581-9554"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34933764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"72","issue":"1","first_page":"247","last_page":"259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9401999711990356,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9401999711990356,"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":0.027000000700354576,"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":0.00430000014603138,"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/transformer","display_name":"Transformer","score":0.5680000185966492},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5562999844551086},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5087000131607056},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.4404999911785126},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4311000108718872},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4016000032424927},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3882000148296356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3578000068664551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394000291824341},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5680000185966492},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4812000095844269},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.4404999911785126},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3418999910354614},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.3391000032424927},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.32120001316070557},{"id":"https://openalex.org/C100921725","wikidata":"https://www.wikidata.org/wiki/Q1650811","display_name":"Spatial frequency","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.2978000044822693},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbc.2025.3635389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbc.2025.3635389","pdf_url":null,"source":{"id":"https://openalex.org/S100142436","display_name":"IEEE Transactions on Broadcasting","issn_l":"0018-9316","issn":["0018-9316","1557-9611"],"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 Broadcasting","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1629255802","display_name":null,"funder_award_id":"U24B20179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1732693589","display_name":null,"funder_award_id":"U22A2022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5292391546","display_name":null,"funder_award_id":"62332017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5655896502","display_name":null,"funder_award_id":"62120106009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7612840180","display_name":null,"funder_award_id":"62372036","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2025768430","https://openalex.org/W2031614119","https://openalex.org/W2040903332","https://openalex.org/W2055116693","https://openalex.org/W2108598243","https://openalex.org/W2118217749","https://openalex.org/W2132347284","https://openalex.org/W2132984323","https://openalex.org/W2135461721","https://openalex.org/W2140196014","https://openalex.org/W2146395539","https://openalex.org/W2490784316","https://openalex.org/W2900996853","https://openalex.org/W2935381027","https://openalex.org/W2963711615","https://openalex.org/W3034469748","https://openalex.org/W3043823510","https://openalex.org/W3093960910","https://openalex.org/W3116647679","https://openalex.org/W3212865599","https://openalex.org/W4307842584","https://openalex.org/W4309134821","https://openalex.org/W4312348190","https://openalex.org/W4312806968","https://openalex.org/W4316660616","https://openalex.org/W4362496227","https://openalex.org/W4385245566","https://openalex.org/W4386075611","https://openalex.org/W4386598339","https://openalex.org/W4386938693","https://openalex.org/W4389253021","https://openalex.org/W4392309256","https://openalex.org/W4392739034","https://openalex.org/W4401717751","https://openalex.org/W4402816554","https://openalex.org/W4402904102","https://openalex.org/W4403943301","https://openalex.org/W4405139810","https://openalex.org/W4410810215","https://openalex.org/W4413144383","https://openalex.org/W4413145538","https://openalex.org/W4413145954"],"related_works":[],"abstract_inverted_index":{"In":[0],"learned":[1],"image":[2],"compression":[3],"(LIC),":[4],"most":[5],"existing":[6],"methods":[7],"process":[8,93],"spatial":[9,68,94,120,147],"domain":[10],"information":[11],"through":[12],"convolutional":[13],"neural":[14],"networks":[15],"(CNNs)":[16],"or":[17],"Transformers.":[18],"However,":[19],"they":[20],"struggle":[21],"to":[22,47,73,91,175,207],"model":[23,79],"frequency-domain":[24],"correlations,":[25,81],"particularly":[26],"high-frequency":[27,35,104,150,204],"detail":[28,36],"correlations":[29,66],"across":[30],"regions.":[31],"They":[32],"suffer":[33],"from":[34],"redundancy":[37],"and":[38,70,95,149,171,188,194],"inefficient":[39],"uniform":[40],"bit":[41,76,165],"allocation,":[42,166],"neither":[43],"of":[44,146,156,202],"which":[45,63],"adapts":[46],"regional":[48],"complexity.":[49],"To":[50,78],"address":[51],"these":[52,80],"issues,":[53],"we":[54],"propose":[55],"the":[56,82,135,157,203],"Spatial-Frequency":[57],"Transformer":[58,84],"Network":[59],"(SFTNet)":[60],"for":[61,163],"LIC,":[62],"models":[64],"cross-domain":[65],"between":[67],"structures":[69],"frequency":[71,96,101],"components":[72,112],"enable":[74],"region-adaptive":[75],"allocation.":[77],"Frequency-aware":[83],"Block":[85],"(FATB)":[86],"employs":[87],"dual":[88],"attention":[89,102,121],"mechanisms":[90],"collaboratively":[92],"components.":[97,131],"Specifically,":[98],"its":[99,118],"intra-block":[100],"enhances":[103],"details":[105,205],"within":[106],"each":[107],"block":[108,141],"by":[109,125,161,186],"using":[110],"low-frequency":[111,130],"as":[113],"local":[114],"structural":[115],"guidance.":[116],"Meanwhile,":[117],"inter-block":[119],"captures":[122],"global":[123],"consistency":[124],"modeling":[126],"cross-block":[127],"dependencies":[128,148],"among":[129],"Building":[132],"on":[133,192],"this,":[134],"Feature":[136],"Re-weighting":[137],"Strategy":[138],"(FRS)":[139],"evaluates":[140],"importance":[142],"via":[143],"joint":[144],"analysis":[145],"energy.":[151],"This":[152],"enables":[153],"dynamic":[154],"alignment":[155],"spatial-frequency":[158],"features":[159],"modeled":[160],"FATB":[162],"adaptive":[164],"prioritizing":[167],"structurally":[168],"complex":[169],"regions":[170],"compressing":[172],"smooth":[173],"areas":[174],"reduce":[176],"redundancy.":[177],"Experimental":[178],"results":[179],"demonstrate":[180],"that":[181],"our":[182],"SFTNet":[183],"outperforms":[184],"VVC":[185],"\u22126.55%":[187],"\u22126.18%":[189],"in":[190],"BD-Rate":[191],"Kodak":[193],"CLIC":[195],"datasets":[196],"while":[197],"achieving":[198],"better":[199],"reconstruction":[200],"quality":[201],"compared":[206],"recent":[208],"LIC":[209],"methods.":[210]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-03T00:00:00"}