{"id":"https://openalex.org/W4415707870","doi":"https://doi.org/10.1109/icme59968.2025.11210074","title":"Dynamic Importance in Diffusion U-Net for Enhanced Image Synthesis","display_name":"Dynamic Importance in Diffusion U-Net for Enhanced Image Synthesis","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707870","doi":"https://doi.org/10.1109/icme59968.2025.11210074"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210074","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 Multimedia and Expo (ICME)","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/A5100442219","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0001-5564-2084"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["CSSE, Shenzhen University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSSE, Shenzhen University,Shenzhen,China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120391454","display_name":"Ziqi He","orcid":"https://orcid.org/0000-0002-0439-1390"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqi He","raw_affiliation_strings":["CSSE, Shenzhen University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSSE, Shenzhen University,Shenzhen,China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018630995","display_name":"Yang Zhou","orcid":"https://orcid.org/0000-0002-8921-312X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhou","raw_affiliation_strings":["CSSE, Shenzhen University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSSE, Shenzhen University,Shenzhen,China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9343000054359436,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9343000054359436,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.008500000461935997,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.006200000178068876,"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/inference","display_name":"Inference","score":0.6988000273704529},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.4918999969959259},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44620001316070557},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44369998574256897},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.42260000109672546},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.4113999903202057},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4027000069618225},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3698999881744385}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6988000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6089000105857849},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.4918999969959259},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44620001316070557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44510000944137573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.42260000109672546},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.4113999903202057},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3140999972820282},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.288100004196167},{"id":"https://openalex.org/C34559072","wikidata":"https://www.wikidata.org/wiki/Q2334061","display_name":"Design of experiments","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210074","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325571","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4386065404","https://openalex.org/W4386113271","https://openalex.org/W4390873195","https://openalex.org/W4390874002","https://openalex.org/W4402704545","https://openalex.org/W4402715897","https://openalex.org/W4402753790","https://openalex.org/W4402775818","https://openalex.org/W4403757510","https://openalex.org/W4404965447","https://openalex.org/W4413144317"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"diffusion":[1],"models":[2],"typically":[3],"employ":[4],"a":[5,61],"U-Net":[6,59],"architecture.":[7,145],"Previous":[8],"studies":[9],"have":[10],"unveiled":[11],"the":[12,18,23,30,51,54,58,66,70,82,88,92,119,122,127,131],"roles":[13],"of":[14,26,53,87,121,130],"attention":[15],"blocks":[16,56,90],"in":[17,85],"U-Net.":[19],"However,":[20],"they":[21],"overlook":[22],"dynamic":[24,83],"evolution":[25],"their":[27,35],"importance":[28,86],"during":[29,69],"inference":[31,123],"process,":[32,124],"which":[33],"hinders":[34],"further":[36],"exploitation":[37],"to":[38,78,104],"improve":[39],"image":[40,106],"applications.":[41],"In":[42],"this":[43],"study,":[44],"we":[45,74,96],"first":[46],"theoretically":[47],"proved":[48],"that,":[49,114],"re-weighting":[50,101],"outputs":[52],"Transformer":[55,89],"within":[57],"is":[60],"\"free":[62],"lunch\"":[63],"for":[64],"improving":[65],"signal-to-noise":[67],"ratio":[68],"sampling":[71],"process.":[72,94],"Next,":[73],"proposed":[75],"Importance":[76],"Probe":[77],"uncover":[79],"and":[80,108,125],"quantify":[81],"shifts":[84],"throughout":[91],"denoising":[93],"Finally,":[95],"design":[97],"an":[98],"adaptive":[99],"importance-based":[100],"schedule":[102],"tailored":[103],"specific":[105],"generation":[107],"editing":[109],"tasks.":[110],"Experimental":[111],"results":[112],"demonstrate":[113],"our":[115],"approach":[116],"significantly":[117],"improves":[118],"efficiency":[120],"enhances":[126],"aesthetic":[128],"quality":[129],"samples":[132],"with":[133],"identity":[134],"consistency.":[135],"Our":[136],"method":[137],"can":[138],"be":[139],"seamlessly":[140],"integrated":[141],"into":[142],"any":[143],"U-Net-based":[144],"Code:":[146],"https://github.com/Hytidel/UNetReweighting":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}