{"id":"https://openalex.org/W4416548863","doi":"https://doi.org/10.1109/iccv51701.2025.01825","title":"DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space","display_name":"DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416548863","doi":"https://doi.org/10.1109/iccv51701.2025.01825"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01825","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.00413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108988214","display_name":"Junyu Chen","orcid":"https://orcid.org/0009-0000-8936-633X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyu Chen","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dongyun Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongyun Zou","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043009334","display_name":"W. L. He","orcid":"https://orcid.org/0000-0001-9822-5037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenkun He","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911197","display_name":"Junsong Chen","orcid":"https://orcid.org/0000-0002-2587-8931"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junsong Chen","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041031140","display_name":"Enze Xie","orcid":"https://orcid.org/0000-0001-6890-1049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enze Xie","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103794871","display_name":"Song Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Han","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087885905","display_name":"Han Cai","orcid":"https://orcid.org/0000-0002-7220-039X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Cai","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"10"},"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":0.9243000149726868,"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":0.9243000149726868,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.00989999994635582,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.005400000140070915,"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/convergence","display_name":"Convergence (economics)","score":0.6865000128746033},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6274999976158142},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4645000100135803},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4465999901294708},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.43869999051094055},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41370001435279846},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.36410000920295715}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6865000128746033},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5565999746322632},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43779999017715454},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C205372313","wikidata":"https://www.wikidata.org/wiki/Q355645","display_name":"Latent image","level":3,"score":0.3555000126361847},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C571446","wikidata":"https://www.wikidata.org/wiki/Q6510183","display_name":"Diffusion equation","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2597000002861023}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01825","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:2508.00413","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00413","pdf_url":"https://arxiv.org/pdf/2508.00413","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.2508.00413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.00413","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.00413","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00413","pdf_url":"https://arxiv.org/pdf/2508.00413","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,71],"present":[1],"DC-AE":[2,135],"1.5,":[3],"a":[4,22,84,89],"new":[5],"family":[6],"of":[7,56,64],"deep":[8],"compression":[9,69],"autoencoders":[10,65],"for":[11,26,37],"high-resolution":[12],"diffusion":[13,38,58,117,122,142],"models.":[14],"Increasing":[15],"the":[16,52,62,94],"autoencoder's":[17],"latent":[18,57,95,99,106,127],"channel":[19],"number":[20],"is":[21],"highly":[23],"effective":[24],"approach":[25,86],"improving":[27],"its":[28],"reconstruction":[29,47],"quality.":[30,48],"However,":[31],"it":[32],"results":[33,144],"in":[34],"slow":[35],"convergence":[36,139],"models,":[39],"leading":[40],"to":[41,76,87,129],"poorer":[42],"generation":[43,154],"quality":[44,53,155],"despite":[45],"better":[46,141,152],"This":[49],"issue":[50],"limits":[51],"upper":[54],"bound":[55],"models":[59],"and":[60,104,140],"hinders":[61],"employment":[63],"with":[66,97,120],"higher":[67],"spatial":[68],"ratios.":[70],"introduce":[72],"two":[73],"key":[74],"innovations":[75],"address":[77],"this":[78],"challenge:":[79],"i)":[80],"Structured":[81],"Latent":[82],"Space,":[83],"training-based":[85],"impose":[88],"desired":[90],"channel-wise":[91],"structure":[92],"on":[93,125],"space":[96],"front":[98],"channels":[100,107,128],"capturing":[101,108],"object":[102,126],"structures":[103],"latter":[105],"image":[109,153],"details;":[110],"ii)":[111],"Augmented":[112],"Diffusion":[113],"Training,":[114],"an":[115],"augmented":[116],"training":[118,123],"strategy":[119],"additional":[121],"objectives":[124],"accelerate":[130],"convergence.":[131],"With":[132],"these":[133],"techniques,":[134],"1.5":[136],"delivers":[137,151],"faster":[138],"scaling":[143],"than":[145,156],"DC-AE.":[146],"On":[147],"ImageNet":[148],"512x512,":[149],"DC-AE-1.5-f64c128":[150],"DC-AE-f32c32":[157],"while":[158],"being":[159],"4x":[160],"faster.":[161],"Code:":[162],"https://github.com/dc-ai-projects/DC-Gen.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}