{"id":"https://openalex.org/W4403790957","doi":"https://doi.org/10.1145/3664647.3681336","title":"Consistency Guided Diffusion Model with Neural Syntax for Perceptual Image Compression","display_name":"Consistency Guided Diffusion Model with Neural Syntax for Perceptual Image Compression","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403790957","doi":"https://doi.org/10.1145/3664647.3681336"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681336","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5021833757","display_name":"Haowei Kuang","orcid":null},"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":true,"raw_author_name":"Haowei Kuang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005921397","display_name":"Yiyang Ma","orcid":"https://orcid.org/0000-0001-7210-4018"},"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":"Yiyang Ma","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070884682","display_name":"Wenhan Yang","orcid":"https://orcid.org/0000-0002-1692-0069"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Yang","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001396675","display_name":"Zongming Guo","orcid":"https://orcid.org/0000-0002-4944-9621"},"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":"Zongming Guo","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100761525","display_name":"Jiaying Liu","orcid":"https://orcid.org/0000-0002-0468-9576"},"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":"Jiaying Liu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021833757"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.7895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73968013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1622","last_page":"1631"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9995999932289124,"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":0.9991999864578247,"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":0.7148207426071167},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6431325078010559},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6392475366592407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.576343834400177},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5659198760986328},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.495383620262146},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.49483412504196167},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.475154846906662},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4693359434604645},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4343816339969635},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40772855281829834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3572070300579071},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3420448899269104},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.26260077953338623},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11540448665618896},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07665732502937317},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.053448110818862915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7148207426071167},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6431325078010559},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6392475366592407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.576343834400177},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5659198760986328},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.495383620262146},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.49483412504196167},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.475154846906662},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4693359434604645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4343816339969635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40772855281829834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3572070300579071},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3420448899269104},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26260077953338623},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11540448665618896},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07665732502937317},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.053448110818862915},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681336","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":32,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W1901129140","https://openalex.org/W2040903332","https://openalex.org/W2046119925","https://openalex.org/W2152281536","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2962802655","https://openalex.org/W2963801130","https://openalex.org/W2971911529","https://openalex.org/W2997572967","https://openalex.org/W3017136408","https://openalex.org/W3034469748","https://openalex.org/W3035574324","https://openalex.org/W3096831136","https://openalex.org/W3102808118","https://openalex.org/W3110286842","https://openalex.org/W3131427579","https://openalex.org/W3155072588","https://openalex.org/W4281986181","https://openalex.org/W4287210973","https://openalex.org/W4309134821","https://openalex.org/W4312590925","https://openalex.org/W4312796583","https://openalex.org/W4312806968","https://openalex.org/W4360897334","https://openalex.org/W4386075858","https://openalex.org/W4386076368","https://openalex.org/W4388188760","https://openalex.org/W4390871851","https://openalex.org/W4390872095","https://openalex.org/W4390873054"],"related_works":["https://openalex.org/W4388713123","https://openalex.org/W3194438104","https://openalex.org/W2570592793","https://openalex.org/W2753140600","https://openalex.org/W1603736412","https://openalex.org/W2354135050","https://openalex.org/W1979017339","https://openalex.org/W4237266227","https://openalex.org/W2372239957","https://openalex.org/W3206149139"],"abstract_inverted_index":{"Diffusion":[0,36],"models":[1],"show":[2],"impressive":[3],"performances":[4],"in":[5,23,88],"image":[6,24,42,48],"generation":[7],"with":[8,51,62,138],"excellent":[9],"perceptual":[10,41,166],"quality.":[11,95],"However,":[12],"its":[13,20],"tendency":[14],"to":[15,57,84,106,148,164],"introduce":[16],"additional":[17],"distortion":[18],"prevents":[19],"direct":[21],"application":[22],"compression.":[25],"To":[26],"address":[27],"the":[28,68,86,89,113,119,125,159],"issue,":[29],"this":[30],"paper":[31],"introduces":[32],"a":[33,52,76,97,132,143],"Consistency":[34],"Guided":[35],"Model":[37],"(CGDM)":[38],"tailored":[39],"for":[40,92],"compression,":[43],"which":[44],"integrates":[45],"an":[46,108],"end-to-end":[47],"compression":[49,69,167],"model":[50],"diffusion-based":[53],"post-processing":[54,71],"network,":[55],"aiming":[56],"learn":[58],"richer":[59],"detail":[60],"representations":[61],"less":[63],"fidelity":[64],"loss.":[65],"In":[66,128],"detail,":[67],"and":[70,75,141,153],"networks":[72],"are":[73],"cascaded":[74],"branch":[77],"of":[78,122,161],"consistency":[79],"guided":[80],"features":[81],"is":[82,104,171],"added":[83],"constrain":[85],"deviation":[87],"diffusion":[90],"process":[91],"better":[93],"reconstruction":[94],"Furthermore,":[96],"Syntax":[98],"driven":[99],"Feature":[100],"Fusion":[101],"(SFF)":[102],"module":[103],"constructed":[105],"take":[107],"extra":[109],"ultra-low":[110],"bitstream":[111],"from":[112,124],"encoding":[114],"end":[115],"as":[116],"input,":[117],"guiding":[118],"adaptive":[120],"fusion":[121],"information":[123],"two":[126],"branches.":[127],"addition,":[129],"we":[130],"design":[131],"globally":[133],"uniform":[134],"boundary":[135],"control":[136],"strategy":[137],"overlapped":[139],"patches":[140],"adopt":[142],"continuous":[144],"online":[145],"optimization":[146],"mode":[147],"improve":[149],"both":[150],"coding":[151],"efficiency":[152],"global":[154],"consistency.":[155],"Extensive":[156],"experiments":[157],"validate":[158],"superiority":[160],"our":[162],"method":[163],"existing":[165],"techniques.":[168],"Our":[169],"project":[170],"publicly":[172],"available":[173],"at:":[174],"https://ellisonkuang.github.io/CGDM.github.io/.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}