{"id":"https://openalex.org/W4413146691","doi":"https://doi.org/10.1109/cvpr52734.2025.00013","title":"Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space","display_name":"Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146691","doi":"https://doi.org/10.1109/cvpr52734.2025.00013"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100698862","display_name":"Yifan Zhou","orcid":"https://orcid.org/0009-0004-6250-8333"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yifan Zhou","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100584895","display_name":"Zeqi Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zeqi Xiao","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330819","display_name":"Shuai Yang","orcid":"https://orcid.org/0000-0002-5889-3812"},"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":"Shuai Yang","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052549072","display_name":"Xingang Pan","orcid":"https://orcid.org/0000-0002-5825-9467"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xingang Pan","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100698862"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":7.4013,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96918756,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9860000014305115,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9860000014305115,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9768000245094299,"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/alias","display_name":"Alias","score":0.8585423827171326},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.7333143949508667},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4859582185745239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4526403546333313},{"id":"https://openalex.org/keywords/anomalous-diffusion","display_name":"Anomalous diffusion","score":0.41213175654411316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3689184784889221},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15825700759887695},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1507658064365387},{"id":"https://openalex.org/keywords/innovation-diffusion","display_name":"Innovation diffusion","score":0.09826529026031494},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.08488136529922485}],"concepts":[{"id":"https://openalex.org/C46681722","wikidata":"https://www.wikidata.org/wiki/Q4725589","display_name":"Alias","level":2,"score":0.8585423827171326},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.7333143949508667},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4859582185745239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4526403546333313},{"id":"https://openalex.org/C164602753","wikidata":"https://www.wikidata.org/wiki/Q567544","display_name":"Anomalous diffusion","level":3,"score":0.41213175654411316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3689184784889221},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15825700759887695},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1507658064365387},{"id":"https://openalex.org/C3017618536","wikidata":"https://www.wikidata.org/wiki/Q304994","display_name":"Innovation diffusion","level":2,"score":0.09826529026031494},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.08488136529922485},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2547468940","https://openalex.org/W1681106482","https://openalex.org/W1540861748","https://openalex.org/W2091442483","https://openalex.org/W1614350759","https://openalex.org/W1967666802","https://openalex.org/W3162900157","https://openalex.org/W1963690572","https://openalex.org/W2617922569","https://openalex.org/W2109649268"],"abstract_inverted_index":{"Latent":[0],"Diffusion":[1],"Models":[2],"(LDMs)":[3],"are":[4],"known":[5],"to":[6,24,43,64,98,131],"have":[7],"an":[8,103],"unstable":[9],"generation":[10],"process,":[11],"where":[12],"even":[13],"small":[14],"perturbations":[15],"or":[16],"shifts":[17],"in":[18,32,68,115],"the":[19,65,95,109,113,116],"input":[20],"noise":[21],"can":[22,54],"lead":[23],"significantly":[25,140],"different":[26],"outputs.":[27],"This":[28],"hinders":[29],"their":[30],"applicability":[31],"applications":[33],"requiring":[34],"consistent":[35,142],"results.":[36],"In":[37],"this":[38],"work,":[39],"we":[40,93],"redesign":[41,94],"LDMs":[42],"enhance":[44],"consistency":[45],"by":[46],"making":[47],"them":[48],"shift-equivariant.":[49],"While":[50],"introducing":[51],"anti-aliasing":[52],"operations":[53],"partially":[55],"improve":[56],"shift-equivariance,":[57],"significant":[58],"aliasing":[59,72],"and":[60,77,81,101,127,153],"inconsistency":[61],"persist":[62],"due":[63],"unique":[66],"challenges":[67],"LDMs,":[69],"including":[70,150],"1)":[71],"amplification":[73],"during":[74],"VAE":[75],"training":[76],"multiple":[78],"U-Net":[79],"inferences,":[80],"2)":[82],"selfattention":[83],"modules":[84,97],"that":[85,106,137],"inherently":[86],"lack":[87],"shift-equivariance.":[88],"To":[89],"address":[90],"these":[91],"issues,":[92],"attention":[96],"be":[99],"shift-equivariant":[100],"propose":[102],"equivariance":[104],"loss":[105],"effectively":[107],"suppresses":[108],"frequency":[110],"bandwidth":[111],"of":[112],"features":[114],"continuous":[117],"domain.":[118],"The":[119],"resulting":[120],"alias-free":[121],"LDM":[122,146],"(AF-LDM)":[123],"achieves":[124],"strong":[125],"shift-equivariance":[126],"is":[128,157],"also":[129],"robust":[130],"irregular":[132],"warping.":[133],"Extensive":[134],"experiments":[135],"demonstrate":[136],"AF-LDM":[138],"produces":[139],"more":[141],"results":[143],"than":[144],"vanilla":[145],"across":[147],"various":[148],"applications,":[149],"video":[151],"editing":[152],"image-to-image":[154],"translation.":[155],"Code":[156],"available":[158],"at:":[159],"https://github.com/SingleZombie/AFLDM":[160]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}