{"id":"https://openalex.org/W7125980533","doi":"https://doi.org/10.1109/smc58881.2025.11342965","title":"Hierarchical Conditional Guidance Diffusion Model for Perceptual Image Compression","display_name":"Hierarchical Conditional Guidance Diffusion Model for Perceptual Image Compression","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125980533","doi":"https://doi.org/10.1109/smc58881.2025.11342965"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124125298","display_name":"Zekai Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekai Ji","raw_affiliation_strings":["North University of China,School of Computer Science and Technology,Taiyuan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North University of China,School of Computer Science and Technology,Taiyuan,China","institution_ids":["https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124125147","display_name":"Jia Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Qin","raw_affiliation_strings":["North University of China,School of Computer Science and Technology,Taiyuan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North University of China,School of Computer Science and Technology,Taiyuan,China","institution_ids":["https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104013224","display_name":"Pinle Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinle Qin","raw_affiliation_strings":["North University of China,School of Computer Science and Technology,Taiyuan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North University of China,School of Computer Science and Technology,Taiyuan,China","institution_ids":["https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124070390","display_name":"Rui Chai","orcid":null},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Chai","raw_affiliation_strings":["North University of China,School of Computer Science and Technology,Taiyuan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North University of China,School of Computer Science and Technology,Taiyuan,China","institution_ids":["https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124088053","display_name":"Jianchao Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianchao Zeng","raw_affiliation_strings":["North University of China,School of Computer Science and Technology,Taiyuan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North University of China,School of Computer Science and Technology,Taiyuan,China","institution_ids":["https://openalex.org/I135714990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101503854","display_name":"Zhipeng Lin","orcid":"https://orcid.org/0000-0003-4106-3668"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Lin","raw_affiliation_strings":["North University of China,School of Computer Science and Technology,Taiyuan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North University of China,School of Computer Science and Technology,Taiyuan,China","institution_ids":["https://openalex.org/I135714990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135714990"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1925","last_page":"1932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.4575999975204468,"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":0.4575999975204468,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.24210000038146973,"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":0.1200999990105629,"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/context","display_name":"Context (archaeology)","score":0.5590000152587891},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.546999990940094},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5209000110626221},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.46860000491142273},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.4397999942302704},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43970000743865967},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43650001287460327},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7389000058174133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6482999920845032},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5590000152587891},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.546999990940094},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48179998993873596},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.4397999942302704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.32249999046325684},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":12,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W2741137940","https://openalex.org/W2769654144","https://openalex.org/W2798581339","https://openalex.org/W3017136408","https://openalex.org/W3202918664","https://openalex.org/W4223425316","https://openalex.org/W4312806968","https://openalex.org/W4386075611","https://openalex.org/W4402299954","https://openalex.org/W4403947072","https://openalex.org/W4404707745"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"diffusion-based":[1],"image":[2,38,55],"compression":[3],"has":[4],"achieved":[5],"significant":[6],"progress":[7],"in":[8,80,191],"terms":[9],"of":[10,27,43,53,78,95],"rate\u2013distortion-perception":[11],"trade-off,":[12],"these":[13,59],"approaches":[14,190],"have":[15],"replaced":[16],"decoders":[17],"with":[18,84],"conditional":[19,171],"diffusion":[20,31,45,96,162],"models":[21,32],"to":[22,74,98,114,133,150],"enhance":[23],"the":[24,36,40,44,50,76,92,161,168],"visual":[25],"quality":[26],"reconstructed":[28],"images.":[29],"However,":[30],"introduce":[33],"noise":[34],"into":[35,160],"input":[37],"during":[39,91,173],"initial":[41],"stages":[42],"process,":[46],"which":[47,81,122,164],"may":[48],"cause":[49],"potential":[51],"degradation":[52],"crucial":[54],"information.":[56],"To":[57],"address":[58],"limitations,":[60],"we":[61,107,141],"propose":[62],"a":[63,109,124,143],"Hierarchical":[64],"Conditional":[65,144],"guidance":[66,90],"Diffusion":[67,146],"model":[68,97],"for":[69],"perceptual":[70],"Image":[71],"Compression":[72],"(HCD-IC)":[73],"ensure":[75,134],"fidelity":[77],"reconstruction,":[79],"hierarchical":[82,125],"features":[83,156,172],"selected":[85],"typical":[86],"context":[87],"provide":[88],"informative":[89],"denoising":[93],"process":[94],"preserve":[99],"both":[100],"structural":[101],"integrity":[102],"and":[103,116,120,129,137,154],"fine":[104],"details.":[105],"Specifically,":[106],"design":[108],"Gated":[110],"Scale-Cross":[111],"module":[112,148],"(GSC)":[113],"integrate":[115,151],"select":[117],"representative":[118],"semantics":[119],"details,":[121],"leverages":[123],"feature":[126],"interaction":[127],"architecture":[128],"dynamic":[130],"gated":[131],"strategy":[132],"more":[135],"robust":[136],"expressive":[138],"representations.":[139],"Furthermore,":[140],"present":[142],"Control":[145],"decode":[147],"(CCD)":[149],"time-step":[152],"information":[153],"latent":[155],"augmented":[157],"by":[158],"GSC":[159],"model,":[163],"can":[165],"dynamically":[166],"acquire":[167],"required":[169],"time-aware":[170],"different":[174],"denoise":[175],"stages.":[176],"Extensive":[177],"experiments":[178],"conducted":[179],"on":[180],"multiple":[181],"public":[182],"datasets":[183],"demonstrate":[184],"that":[185],"our":[186],"method":[187],"outperforms":[188],"state-of-the-art":[189],"various":[192],"quantitative":[193],"realism":[194],"metrics.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}