{"id":"https://openalex.org/W4400034378","doi":"https://doi.org/10.1109/pcs60826.2024.10566428","title":"Wavelet-like Transform with Subbands Fusion in Decoupled Structure for Deep Image Compression","display_name":"Wavelet-like Transform with Subbands Fusion in Decoupled Structure for Deep Image Compression","publication_year":2024,"publication_date":"2024-06-12","ids":{"openalex":"https://openalex.org/W4400034378","doi":"https://doi.org/10.1109/pcs60826.2024.10566428"},"language":"en","primary_location":{"id":"doi:10.1109/pcs60826.2024.10566428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pcs60826.2024.10566428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Picture Coding Symposium (PCS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101818500","display_name":"Ke Ma","orcid":"https://orcid.org/0000-0002-4720-7151"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Ma","raw_affiliation_strings":["University of Science and Technology of China,HeFei,Anhui,P.R. China,230026"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,HeFei,Anhui,P.R. China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101519265","display_name":"Yaojun Wu","orcid":"https://orcid.org/0000-0002-8138-4186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaojun Wu","raw_affiliation_strings":["Bytedance Inc.,San Diego,CA,USA,92122"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc.,San Diego,CA,USA,92122","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102714187","display_name":"Zhaobin Zhang","orcid":"https://orcid.org/0000-0001-5961-5163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaobin Zhang","raw_affiliation_strings":["Bytedance Inc.,San Diego,CA,USA,92122"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc.,San Diego,CA,USA,92122","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015597250","display_name":"Semih Esenlik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Semih Esenlik","raw_affiliation_strings":["Bytedance Inc.,San Diego,CA,USA,92122"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc.,San Diego,CA,USA,92122","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656317","display_name":"Xiaoyan Sun","orcid":"https://orcid.org/0000-0003-3638-5566"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Sun","raw_affiliation_strings":["University of Science and Technology of China,HeFei,Anhui,P.R. China,230026"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,HeFei,Anhui,P.R. China,230026","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323986","display_name":"Kai Zhang","orcid":"https://orcid.org/0000-0002-6627-0009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Zhang","raw_affiliation_strings":["Bytedance Inc.,San Diego,CA,USA,92122"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc.,San Diego,CA,USA,92122","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418973","display_name":"Zhang Li","orcid":"https://orcid.org/0009-0003-8559-4599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Bytedance Inc.,San Diego,CA,USA,92122"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc.,San Diego,CA,USA,92122","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.934499979019165,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.934499979019165,"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":0.9243000149726868,"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/wavelet-transform","display_name":"Wavelet transform","score":0.6447219848632812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6395986676216125},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5837405920028687},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5728700160980225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5122324824333191},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45889970660209656},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4552856385707855},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43101903796195984},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.42551642656326294},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3884522020816803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3227279782295227},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14581146836280823}],"concepts":[{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.6447219848632812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6395986676216125},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5837405920028687},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5728700160980225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5122324824333191},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45889970660209656},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4552856385707855},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43101903796195984},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.42551642656326294},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3884522020816803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3227279782295227},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14581146836280823},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pcs60826.2024.10566428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pcs60826.2024.10566428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Picture Coding Symposium (PCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W66275760","https://openalex.org/W2785562966","https://openalex.org/W2893920456","https://openalex.org/W2949361041","https://openalex.org/W2964098744","https://openalex.org/W3017123215","https://openalex.org/W3034469748","https://openalex.org/W3088142143","https://openalex.org/W3133927215","https://openalex.org/W3179468628","https://openalex.org/W3206996732","https://openalex.org/W4386609189","https://openalex.org/W4391799317","https://openalex.org/W6754634825","https://openalex.org/W6755487101","https://openalex.org/W6798322722"],"related_works":["https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W2116037602","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2549658594","https://openalex.org/W2095903272","https://openalex.org/W2077021924","https://openalex.org/W2370195708","https://openalex.org/W1490651872"],"abstract_inverted_index":{"Wavelet-like":[0],"transform,":[1],"based":[2],"on":[3,140],"convolutional":[4],"neural":[5],"network":[6],"(CNN),":[7],"is":[8,53],"content-adaptive":[9],"and":[10,64],"has":[11],"made":[12],"remarkable":[13],"achievements":[14],"in":[15,27,38,159],"end-to-end":[16,157],"image":[17,48],"compression.":[18],"However,":[19],"the":[20,28,50,56,62,116,124,129,136,141,147],"subsequent":[21],"sequential":[22],"processing":[23],"of":[24,76],"each":[25],"subband":[26,86],"entropy":[29],"module":[30],"takes":[31],"a":[32,81,109],"relatively":[33],"long":[34],"decoding":[35,126,137],"time,":[36],"resulting":[37],"incon-venience":[39],"for":[40,46,85],"real-world":[41],"applications.":[42],"In":[43,114],"this":[44],"work,":[45],"lossy":[47],"compression,":[49],"wavelet-like":[51],"transform":[52,66],"transplanted":[54],"into":[55],"prevailing":[57],"autoencoder":[58],"structure":[59,158],"to":[60,68,99,103,107,154],"enhance":[61],"analysis":[63],"synthesis":[65],"due":[67],"its":[69],"excellent":[70],"decomposition":[71],"capability.":[72],"The":[73,93],"obtained":[74],"subbands":[75,101],"different":[77,100],"frequencies":[78],"will":[79,96],"undergo":[80],"hierarchical":[82],"decorrelation":[83],"architecture":[84,121],"fusion,":[87],"also":[88],"called":[89],"cross":[90],"fusing":[91],"module.":[92],"specialized":[94],"treatment":[95],"be":[97],"applied":[98],"according":[102],"their":[104],"spatial":[105],"resolution":[106],"attain":[108],"more":[110],"compact":[111],"latent":[112],"representation.":[113],"addition,":[115],"proposed":[117,148],"solution":[118],"features":[119],"an":[120],"that":[122,146],"decouples":[123],"arithmetic":[125],"process":[127],"from":[128],"sample":[130],"prediction":[131],"process,":[132],"which":[133],"significantly":[134],"reduces":[135],"complexity.":[138],"Experiments":[139],"Kodak":[142],"test":[143],"set":[144],"show":[145],"method":[149],"achieves":[150],"\u22123.04%":[151],"BD-Rate":[152],"compared":[153],"existing":[155],"decoupled":[156],"RGB":[160],"Peak":[161],"Signal-to-Noise":[162],"Ratio":[163],"(PSNR).":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}