{"id":"https://openalex.org/W4414711592","doi":"https://doi.org/10.1109/iccv51701.2025.01618","title":"Latent Diffusion Models With Masked Autoencoders","display_name":"Latent Diffusion Models With Masked Autoencoders","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414711592","doi":"https://doi.org/10.1109/iccv51701.2025.01618"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01618","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.09984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100366249","display_name":"Junho Lee","orcid":"https://orcid.org/0000-0002-8001-700X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Junho Lee","raw_affiliation_strings":["Seoul National University,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109776626","display_name":"J. Shin","orcid":"https://orcid.org/0009-0004-3306-4518"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongwoo Shin","raw_affiliation_strings":["Seoul National University,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042054457","display_name":"Hyung Wook Choi","orcid":"https://orcid.org/0000-0001-6151-5356"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungwook Choi","raw_affiliation_strings":["Seoul National University,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067433666","display_name":"Joonseok Lee","orcid":"https://orcid.org/0000-0001-9551-6402"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonseok Lee","raw_affiliation_strings":["Seoul National University,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100366249"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13294349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17422","last_page":"17431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7159000039100647,"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/T10028","display_name":"Topic Modeling","score":0.7159000039100647,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5182999968528748},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5177000164985657},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43380001187324524},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4106999933719635},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4027000069618225},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.3531000018119812},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3249000012874603}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6779000163078308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6599000096321106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43380001187324524},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4106999933719635},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01618","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:2507.09984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.09984","pdf_url":"https://arxiv.org/pdf/2507.09984","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2507.09984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.09984","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.09984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.09984","pdf_url":"https://arxiv.org/pdf/2507.09984","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,26],"spite":[1],"of":[2,6,20,33,70],"the":[3,14,21,31,71,82],"remarkable":[4],"potential":[5],"Latent":[7,86],"Diffusion":[8,87],"Models":[9,88],"(LDMs)":[10],"in":[11,35],"image":[12],"generation,":[13],"desired":[15],"properties":[16],"and":[17,37,47,62],"optimal":[18],"design":[19],"autoencoders":[22,34,54],"have":[23],"been":[24],"underexplored.":[25],"this":[27],"work,":[28],"we":[29],"analyze":[30],"role":[32],"LDMs":[36],"identify":[38],"three":[39,60],"key":[40],"properties:":[41],"latent":[42],"smoothness,":[43],"perceptual":[44],"compression":[45],"quality,":[46],"reconstruction":[48],"quality.":[49],"We":[50,78],"demonstrate":[51],"that":[52],"existing":[53],"fail":[55],"to":[56],"simultaneously":[57],"satisfy":[58],"all":[59],"properties,":[61],"propose":[63],"Variational":[64],"Masked":[65,76,90],"AutoEncoders":[66,91],"(VMAEs),":[67],"taking":[68],"advantage":[69],"hierarchical":[72],"features":[73],"maintained":[74],"by":[75],"AutoEncoders.":[77],"integrate":[79],"VMAEs":[80],"into":[81],"LDM":[83],"framework,":[84],"introducing":[85],"with":[89],"(LDMAEs).":[92],"Our":[93],"code":[94],"is":[95],"available":[96],"at":[97],"https://github.com/isno0907/ldmae.":[98]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}