{"id":"https://openalex.org/W4406859033","doi":"https://doi.org/10.1109/vcip63160.2024.10849862","title":"Perceptual Image Compression With Conditional Diffusion Transformers","display_name":"Perceptual Image Compression With Conditional Diffusion Transformers","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4406859033","doi":"https://doi.org/10.1109/vcip63160.2024.10849862"},"language":"en","primary_location":{"id":"doi:10.1109/vcip63160.2024.10849862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip63160.2024.10849862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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/A5101979810","display_name":"Rui Mao","orcid":"https://orcid.org/0009-0003-6545-795X"},"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":true,"raw_author_name":"Rui Mao","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069359435","display_name":"Xinmin Feng","orcid":"https://orcid.org/0000-0001-9287-858X"},"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":"Xinmin Feng","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101807983","display_name":"Changsheng Gao","orcid":"https://orcid.org/0009-0008-8787-8014"},"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":"Changsheng Gao","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103580985","display_name":"Li Li","orcid":null},"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":"Li Li","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453037","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0002-0853-1792"},"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":"Dong Liu","raw_affiliation_strings":["University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100537852","display_name":"Xiaoyan Sun","orcid":null},"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,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101979810"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27347351,"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":0.973800003528595,"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":0.973800003528595,"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":0.9465000033378601,"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":0.5936462879180908},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.5324916243553162},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47790154814720154},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.47265851497650146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47127506136894226},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4509087800979614},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4383099377155304},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2440977394580841},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.21341943740844727},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2095295488834381},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12674453854560852},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08739039301872253},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0745459794998169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5936462879180908},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.5324916243553162},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47790154814720154},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.47265851497650146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47127506136894226},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4509087800979614},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4383099377155304},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2440977394580841},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.21341943740844727},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2095295488834381},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12674453854560852},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08739039301872253},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0745459794998169},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip63160.2024.10849862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip63160.2024.10849862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2769654144","https://openalex.org/W2785562966","https://openalex.org/W2962785568","https://openalex.org/W2997508111","https://openalex.org/W3017136408","https://openalex.org/W3160589897","https://openalex.org/W3202918664","https://openalex.org/W4312933868","https://openalex.org/W4316830033","https://openalex.org/W4385245566","https://openalex.org/W4386065641","https://openalex.org/W6637373629","https://openalex.org/W6751862702","https://openalex.org/W6754405603","https://openalex.org/W6754634825","https://openalex.org/W6779823529","https://openalex.org/W6780365925","https://openalex.org/W6792313209","https://openalex.org/W6843772381","https://openalex.org/W6849095040","https://openalex.org/W6852953693"],"related_works":["https://openalex.org/W2521595930","https://openalex.org/W4243608781","https://openalex.org/W3165542721","https://openalex.org/W4313046148","https://openalex.org/W1939109514","https://openalex.org/W4378191574","https://openalex.org/W2129829718","https://openalex.org/W1843792225","https://openalex.org/W2751842002","https://openalex.org/W2161981399"],"abstract_inverted_index":{"Generative":[0],"models":[1],"have":[2,17],"significantly":[3],"advanced":[4],"generative":[5,69,98],"AI,":[6],"particularly":[7],"in":[8,22],"image":[9,23,51,123],"and":[10,35],"video":[11],"generation.":[12],"Recognizing":[13],"their":[14,20],"potential,":[15],"researchers":[16],"begun":[18],"exploring":[19],"application":[21],"compression.":[24],"However,":[25],"existing":[26,121],"methods":[27,125],"face":[28],"two":[29,45],"primary":[30],"challenges:":[31],"limited":[32],"performance":[33,63],"improvement":[34],"high":[36],"model":[37,83,129],"complexity.":[38,130],"In":[39],"this":[40],"paper,":[41],"to":[42],"address":[43,81],"these":[44],"challenges,":[46],"we":[47,71,86,100],"propose":[48],"a":[49,56,109],"perceptual":[50,122],"compression":[52,62,124],"solution":[53],"by":[54],"introducing":[55],"conditional":[57],"diffusion":[58,77,89],"model.":[59],"Given":[60],"that":[61,117],"heavily":[64],"depends":[65],"on":[66,75],"the":[67,76,82,88,103],"decoder\u2019s":[68],"capability,":[70,99],"base":[72],"our":[73,118],"decoder":[74,104],"transformer":[78,90],"architecture.":[79],"To":[80],"complexity":[84],"problem,":[85],"implement":[87],"architecture":[91],"with":[92,96,105],"Swin":[93],"transformer.":[94],"Equipped":[95],"enhanced":[97],"further":[101],"augment":[102],"informative":[106],"features":[107],"using":[108],"multi-scale":[110],"feature":[111],"fusion":[112],"module.":[113],"Experimental":[114],"results":[115],"demonstrate":[116],"approach":[119],"surpasses":[120],"while":[126],"achieving":[127],"lower":[128]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
