{"id":"https://openalex.org/W7131290252","doi":"https://doi.org/10.1109/vcip67698.2025.11396876","title":"One-Step Diffusion for Perceptual Image Compression","display_name":"One-Step Diffusion for Perceptual Image Compression","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7131290252","doi":"https://doi.org/10.1109/vcip67698.2025.11396876"},"language":null,"primary_location":{"id":"doi:10.1109/vcip67698.2025.11396876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","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/A5124923978","display_name":"Yiwen Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Jia","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025665266","display_name":"Hao Wei","orcid":"https://orcid.org/0009-0009-8717-652X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wei","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015778825","display_name":"Yanhui Zhou","orcid":"https://orcid.org/0000-0002-4130-0195"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhui Zhou","raw_affiliation_strings":["Xi’an Jiaotong University,School of Information and Telecommunication,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Information and Telecommunication,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025083064","display_name":"Chenyang Ge","orcid":"https://orcid.org/0000-0003-0756-3706"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Ge","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66421899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.703000009059906,"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":0.703000009059906,"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":0.06880000233650208,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.016699999570846558,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/inference","display_name":"Inference","score":0.593999981880188},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.5745999813079834},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5285000205039978},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.49050000309944153},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4643000066280365},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4553999900817871},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.40950000286102295},{"id":"https://openalex.org/keywords/compression-artifact","display_name":"Compression artifact","score":0.40459999442100525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4004000127315521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512999773025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6970999836921692},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6000000238418579},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.5745999813079834},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.49050000309944153},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.40459999442100525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3970000147819519},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.3926999866962433},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36559998989105225},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C54243161","wikidata":"https://www.wikidata.org/wiki/Q39333","display_name":"Texture compression","level":5,"score":0.30320000648498535},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.2671000063419342},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip67698.2025.11396876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","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":20,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W2040903332","https://openalex.org/W2768814045","https://openalex.org/W2962785568","https://openalex.org/W2981613960","https://openalex.org/W3017136408","https://openalex.org/W3034469748","https://openalex.org/W3168982742","https://openalex.org/W3206996732","https://openalex.org/W4281986181","https://openalex.org/W4312806968","https://openalex.org/W4312933868","https://openalex.org/W4385815481","https://openalex.org/W4386065641","https://openalex.org/W4386075611","https://openalex.org/W4390492193","https://openalex.org/W4390873054","https://openalex.org/W4402299954","https://openalex.org/W4404707745","https://openalex.org/W4415824462"],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"image":[1,49],"compression":[2,50,105],"methods":[3],"have":[4],"achieved":[5],"notable":[6],"progress,":[7],"delivering":[8],"high":[9],"perceptual":[10,66],"quality":[11,67],"at":[12,126],"low":[13],"bitrates.":[14],"However,":[15],"their":[16],"practical":[17],"deployment":[18],"is":[19],"hindered":[20],"by":[21],"significant":[22],"inference":[23,61,112],"latency":[24],"and":[25,94,122],"heavy":[26],"computational":[27],"overhead,":[28],"primarily":[29],"due":[30],"to":[31,115],"the":[32,65,86],"large":[33],"number":[34],"of":[35,68,82],"denoising":[36],"steps":[37],"required":[38],"during":[39],"decoding.":[40],"To":[41,63],"address":[42],"this":[43],"problem,":[44],"we":[45,71],"propose":[46],"a":[47,55,73,109],"diffusion-based":[48,117],"method":[51,102],"that":[52,75,88,100],"requires":[53],"only":[54],"single-step":[56],"diffusion":[57],"process,":[58],"significantly":[59],"improving":[60],"speed.":[62],"enhance":[64],"reconstructed":[69],"images,":[70],"introduce":[72],"discriminator":[74],"operates":[76],"on":[77],"compact":[78],"feature":[79],"representations":[80],"instead":[81],"raw":[83],"pixels,":[84],"leveraging":[85],"fact":[87],"features":[89],"better":[90],"capture":[91],"high-level":[92],"texture":[93],"structural":[95],"details.":[96],"Experimental":[97],"results":[98],"show":[99],"our":[101],"delivers":[103],"comparable":[104],"performance":[106],"while":[107],"offering":[108],"46\u00d7":[110],"faster":[111],"speed":[113],"compared":[114],"recent":[116],"approaches.":[118],"The":[119],"source":[120],"code":[121],"models":[123],"are":[124],"available":[125],"https://github.com/cheesejiang/OSDiff.":[127]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-06T00:00:00"}