{"id":"https://openalex.org/W7118288042","doi":"https://doi.org/10.1109/tcsvt.2026.3651547","title":"Syntax-Driven Multi-Realism Image Compression With Consistency Guided Diffusion Model","display_name":"Syntax-Driven Multi-Realism Image Compression With Consistency Guided Diffusion Model","publication_year":2026,"publication_date":"2026-01-06","ids":{"openalex":"https://openalex.org/W7118288042","doi":"https://doi.org/10.1109/tcsvt.2026.3651547"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3651547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3651547","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/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":false,"raw_author_name":"Haowei Kuang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-4975-6474","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, 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, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-1692-0069","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":null,"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, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4944-9621","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122266767","display_name":"Jiaying Liu","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":false,"raw_author_name":"Jiaying Liu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0468-9576","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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8119,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92048297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"5","first_page":"6211","last_page":"6224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.4657000005245209,"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":0.4657000005245209,"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":0.3271999955177307,"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":0.06270000338554382,"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/image-compression","display_name":"Image compression","score":0.515500009059906},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4169999957084656},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41530001163482666},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.399399995803833},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.39419999718666077},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.3788999915122986},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.374099999666214},{"id":"https://openalex.org/keywords/anisotropic-diffusion","display_name":"Anisotropic diffusion","score":0.3668999969959259},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.36320000886917114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477999925613403},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.515500009059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123000144958496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4417000114917755},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.374099999666214},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.35580000281333923},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3312000036239624},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2815000116825104},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.2800000011920929},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3651547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3651547","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W1901129140","https://openalex.org/W2040903332","https://openalex.org/W2046119925","https://openalex.org/W2146395539","https://openalex.org/W2152281536","https://openalex.org/W2741137940","https://openalex.org/W2798581339","https://openalex.org/W2962785568","https://openalex.org/W2962802655","https://openalex.org/W2963801130","https://openalex.org/W2981613960","https://openalex.org/W2997572967","https://openalex.org/W3009294957","https://openalex.org/W3034469748","https://openalex.org/W3096831136","https://openalex.org/W3110286842","https://openalex.org/W3131427579","https://openalex.org/W3160589897","https://openalex.org/W3168982742","https://openalex.org/W3202918664","https://openalex.org/W4281986181","https://openalex.org/W4309134821","https://openalex.org/W4312590925","https://openalex.org/W4312796583","https://openalex.org/W4312806968","https://openalex.org/W4385245566","https://openalex.org/W4386065641","https://openalex.org/W4386075611","https://openalex.org/W4386075858","https://openalex.org/W4386076368","https://openalex.org/W4388188760","https://openalex.org/W4390871851","https://openalex.org/W4390871935","https://openalex.org/W4390872095","https://openalex.org/W4390873054","https://openalex.org/W4392739034","https://openalex.org/W4394625726","https://openalex.org/W4394625730","https://openalex.org/W4396982411","https://openalex.org/W4398164016","https://openalex.org/W4400799775","https://openalex.org/W4402299954","https://openalex.org/W4402979763","https://openalex.org/W4405600801","https://openalex.org/W4408564084","https://openalex.org/W4411142954","https://openalex.org/W7160014897"],"related_works":[],"abstract_inverted_index":{"Given":[0],"the":[1,33,109,116,140,145,151,167,182,216,228],"challenge":[2],"of":[3,27,52,111,171,218,230],"balancing":[4],"high":[5,45],"fidelity":[6],"with":[7,24,44,174],"perceptual":[8,46],"quality,":[9],"multi-realism":[10,77,103],"image":[11,73,78,104],"compression":[12,79,223],"is":[13,57,129,163],"developed":[14],"to":[15,18,29,60,84,86,107,131,143,154,165,205],"adapt":[16,85],"flexibly":[17],"varying":[19],"requirements.":[20,88],"It":[21],"allows":[22],"images":[23,43],"different":[25,87],"levels":[26],"realism":[28],"be":[30],"decoded":[31],"from":[32],"same":[34],"bit":[35],"stream.":[36],"Diffusion":[37,97],"models":[38],"are":[39],"known":[40],"for":[41,102],"generating":[42],"quality.":[47],"However,":[48],"their":[49,69],"inherent":[50],"process":[51,153],"adding":[53],"noise":[54],"and":[55,62,121,185,198,209],"denoising":[56],"often":[58],"difficult":[59],"control":[61,83,108,187,211],"will":[63],"bring":[64],"more":[65],"distortion.":[66],"This":[67],"limits":[68],"direct":[70],"application":[71],"in":[72,76,150],"compression,":[74,105],"especially":[75],"which":[80,180],"requires":[81],"precise":[82],"To":[89],"address":[90],"this":[91],"issue,":[92],"we":[93,191],"propose":[94],"aConsistency":[95],"Guided":[96],"Modelas":[98],"a":[99,158,193,200],"post-processing":[100],"network":[101],"aiming":[106],"addition":[110],"detail":[112],"representations,":[113],"thereby":[114],"adjusting":[115],"trade-off":[117,186,210],"between":[118],"subjective":[119],"quality":[120],"fidelity.":[122,156],"In":[123,189],"detail,":[124],"our":[125,219],"proposed":[126],"novel":[127],"method":[128,204,220],"crafted":[130],"introduce":[132],"an":[133,175],"additional":[134],"consistency":[135],"guided":[136],"feature":[137,160],"branch":[138],"into":[139],"diffusion":[141,152],"model":[142],"constrain":[144],"deviation":[146],"caused":[147],"by":[148],"randomness":[149],"ensure":[155],"Furthermore,":[157],"syntax-driven":[159],"fusion":[161,170],"module":[162],"constructed":[164],"guide":[166],"information":[168,184],"adaptive":[169],"two":[172],"branches":[173],"input":[176],"extra":[177],"ultra-low":[178],"stream,":[179],"contains":[181],"context":[183],"information.":[188],"addition,":[190],"design":[192],"warm-up":[194],"based":[195],"training":[196],"strategy":[197],"adopt":[199],"continuous":[201],"online":[202],"optimization":[203],"improve":[206],"coding":[207],"efficiency":[208],"precision.":[212],"Extensive":[213],"experiments":[214],"validate":[215],"superiority":[217],"over":[221],"existing":[222],"techniques,":[224],"as":[225,227],"well":[226],"effectiveness":[229],"each":[231],"component.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-01-08T00:00:00"}