{"id":"https://openalex.org/W4404450875","doi":"https://doi.org/10.1109/iccv51701.2025.01643","title":"Golden Noise for Diffusion Models: A Learning Framework","display_name":"Golden Noise for Diffusion Models: A Learning Framework","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404450875","doi":"https://doi.org/10.1109/iccv51701.2025.01643"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.09502","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038525380","display_name":"Zikai Zhou","orcid":"https://orcid.org/0000-0002-4577-9826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zikai Zhou","raw_affiliation_strings":["HKUST-GZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST-GZ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073038991","display_name":"Shitong Shao","orcid":"https://orcid.org/0000-0003-4689-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shitong Shao","raw_affiliation_strings":["HKUST-GZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST-GZ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032096158","display_name":"Lichen Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lichen Bai","raw_affiliation_strings":["HKUST-GZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST-GZ","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shufei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Shufei Zhang","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058662188","display_name":"Zhiqiang Xu","orcid":"https://orcid.org/0000-0002-3995-4448"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Zhiqiang Xu","raw_affiliation_strings":["MBZUAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101460966","display_name":"Bo Han","orcid":"https://orcid.org/0000-0002-6089-9797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Han","raw_affiliation_strings":["HKBU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKBU","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066773635","display_name":"Zeke Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeke Xie","raw_affiliation_strings":["HKUST-GZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST-GZ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00067085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17688","last_page":"17697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.06080000102519989,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10320","display_name":"Neural Networks and Applications","score":0.06080000102519989,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/diffusion","display_name":"Diffusion","score":0.5876979231834412},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.537619411945343},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.519291341304779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41462013125419617},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.35147321224212646},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.31731241941452026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3012480139732361},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10213735699653625},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.0637316107749939}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5876979231834412},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.537619411945343},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.519291341304779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41462013125419617},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.35147321224212646},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.31731241941452026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3012480139732361},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10213735699653625},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0637316107749939},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.09502","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.09502","pdf_url":"https://arxiv.org/pdf/2411.09502","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.09502","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.09502","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.09502","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.09502","pdf_url":"https://arxiv.org/pdf/2411.09502","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1502198272","https://openalex.org/W2017540542","https://openalex.org/W2006758266","https://openalex.org/W2066504725","https://openalex.org/W1527813328","https://openalex.org/W2073254488","https://openalex.org/W2104764082","https://openalex.org/W2070530935","https://openalex.org/W1549310245"],"abstract_inverted_index":{"Text-to-image":[0],"diffusion":[1,59,125,236],"model":[2],"is":[3,203,245],"a":[4,13,17,45,72,83,88,93,121,130,138,168,179,183,195,246,254,269,274],"popular":[5],"paradigm":[6],"that":[7,24,30,113,143,173,251],"synthesizes":[8],"personalized":[9],"images":[10,233],"by":[11,91],"providing":[12],"text":[14,100,122,156,213],"prompt":[15,110,123,132,141,171,198],"and":[16,36,136,150,208,223,241,248,262],"random":[18,84,148,180,275],"Gaussian":[19,85],"noise.":[20,185],"While":[21],"people":[22],"observe":[23],"some":[25],"noises":[26,57,149,152],"are":[27],"``golden":[28],"noises''":[29],"can":[31,174,191],"achieve":[32],"better":[33],"text-image":[34],"alignment":[35],"higher":[37],"human":[38],"preference":[39],"than":[40],"others,":[41],"we":[42,61,70,105,128,166],"still":[43],"lack":[44],"machine":[46],"learning":[47],"framework":[48,112],"to":[49,177,210],"obtain":[50],"those":[51],"golden":[52,56,89,117,151,184,188,270],"noises.":[53],"To":[54],"learn":[55,176],"for":[58,124,199],"sampling,":[60],"mainly":[62],"make":[63],"three":[64],"contributions":[65],"in":[66,205],"this":[67],"paper.":[68],"First,":[69],"identify":[71],"new":[73],"concept":[74],"termed":[75],"the":[76,99,103,108,154,159,163,211,220,229,279],"\\textit{noise":[77,109,140,170],"prompt},":[78],"which":[79],"aims":[80],"at":[81],"turning":[82],"noise":[86,90,118,131,181,189,271,276],"into":[87,182],"adding":[92],"small":[94,169,247],"desirable":[95],"perturbation":[96,190],"derived":[97],"from":[98],"prompt.":[101,214],"Following":[102],"concept,":[104],"first":[106],"formulate":[107],"learning}":[111],"systematically":[114],"learns":[115],"``prompted''":[116],"associated":[119,155],"with":[120,153,257],"models.":[126],"Second,":[127],"design":[129],"data":[133],"collection":[134],"pipeline":[135],"collect":[137],"large-scale":[139],"dataset}~(NPD)":[142],"contains":[144],"100k":[145],"pairs":[146],"of":[147,197,225,231,273],"prompts.":[157],"With":[158],"prepared":[160],"NPD":[161],"as":[162,194,201,253,265],"training":[164],"dataset,":[165],"trained":[167],"network}~(NPNet)":[172],"directly":[175],"transform":[178],"The":[186],"learned":[187],"be":[192],"considered":[193],"kind":[196],"noise,":[200],"it":[202,266],"rich":[204],"semantic":[206],"information":[207],"tailored":[209],"given":[212],"Third,":[215],"our":[216],"extensive":[217],"experiments":[218],"demonstrate":[219],"impressive":[221],"effectiveness":[222],"generalization":[224],"NPNet":[226,244],"on":[227],"improving":[228],"quality":[230],"synthesized":[232],"across":[234],"various":[235],"models,":[237],"including":[238],"SDXL,":[239],"DreamShaper-xl-v2-turbo,":[240],"Hunyuan-DiT.":[242],"Moreover,":[243],"efficient":[249],"controller":[250],"acts":[252],"plug-and-play":[255],"module":[256],"very":[258],"limited":[259],"additional":[260],"inference":[261],"computational":[263],"costs,":[264],"just":[267],"provides":[268],"instead":[272],"without":[277],"accessing":[278],"original":[280],"pipeline.":[281]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}