{"id":"https://openalex.org/W4377131053","doi":"https://doi.org/10.48550/arxiv.2305.10853","title":"LDM3D: Latent Diffusion Model for 3D","display_name":"LDM3D: Latent Diffusion Model for 3D","publication_year":2023,"publication_date":"2023-05-18","ids":{"openalex":"https://openalex.org/W4377131053","doi":"https://doi.org/10.48550/arxiv.2305.10853"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.10853","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.10853","pdf_url":"https://arxiv.org/pdf/2305.10853","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.10853","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081879623","display_name":"Gabriela Ben Melech Stan","orcid":"https://orcid.org/0000-0001-6893-6647"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Stan, Gabriela Ben Melech","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002432646","display_name":"Diana Wofk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wofk, Diana","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101204611","display_name":"Scottie Fox","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fox, Scottie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112919438","display_name":"Alex Redden","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Redden, Alex","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049184990","display_name":"W. O. Saxton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saxton, Will","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101204612","display_name":"Jean Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Jean","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011321921","display_name":"Estelle Aflalo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aflalo, Estelle","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003744098","display_name":"Shao-Yen Tseng","orcid":"https://orcid.org/0000-0003-1795-8330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tseng, Shao-Yen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112027547","display_name":"F\u00e1bio Nonato","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nonato, Fabio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108462329","display_name":"Matthias M\u00fcller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muller, Matthias","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087898808","display_name":"Vasudev Lal","orcid":"https://orcid.org/0000-0002-5907-9898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lal, Vasudev","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5081879623"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9898999929428101,"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":0.9898999929428101,"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/T12290","display_name":"Human Motion and Animation","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9797000288963318,"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/computer-science","display_name":"Computer science","score":0.7657516002655029},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6369401216506958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6030185222625732},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5495707392692566},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5170239210128784},{"id":"https://openalex.org/keywords/entertainment","display_name":"Entertainment","score":0.5159750580787659},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4926970303058624},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4885212182998657},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4776008129119873},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4675285816192627},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4652135670185089},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0786692202091217},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.07097986340522766},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07059159874916077},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06432688236236572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657516002655029},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6369401216506958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6030185222625732},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5495707392692566},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5170239210128784},{"id":"https://openalex.org/C512170562","wikidata":"https://www.wikidata.org/wiki/Q173799","display_name":"Entertainment","level":2,"score":0.5159750580787659},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4926970303058624},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4885212182998657},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4776008129119873},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4675285816192627},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4652135670185089},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0786692202091217},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.07097986340522766},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07059159874916077},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06432688236236572},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.10853","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.10853","pdf_url":"https://arxiv.org/pdf/2305.10853","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.10853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.10853","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:2305.10853","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.10853","pdf_url":"https://arxiv.org/pdf/2305.10853","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"This":[0,81],"research":[1],"paper":[2,103],"proposes":[3],"a":[4,20,39,88,105],"Latent":[5],"Diffusion":[6],"Model":[7],"for":[8],"3D":[9],"(LDM3D)":[10],"that":[11],"generates":[12],"both":[13],"image":[14],"and":[15,49,51,69,75,95,99,114,117,123,129],"depth":[16,47,70],"map":[17,48],"data":[18],"from":[19,30,93],"given":[21],"text":[22,31],"prompt,":[23],"allowing":[24],"users":[25],"to":[26,72,86,97,108,125],"generate":[27],"RGBD":[28],"images":[29,68],"prompts.":[32],"The":[33],"LDM3D":[34,122],"model":[35],"is":[36],"fine-tuned":[37],"on":[38],"dataset":[40],"of":[41,91,111,121],"tuples":[42],"containing":[43],"an":[44,59],"RGB":[45,67],"image,":[46],"caption,":[50],"validated":[52],"through":[53],"extensive":[54],"experiments.":[55],"We":[56],"also":[57],"develop":[58],"application":[60],"called":[61],"DepthFusion,":[62],"which":[63],"uses":[64],"the":[65,84,109,119,136],"generated":[66],"maps":[71],"create":[73],"immersive":[74],"interactive":[76],"360-degree-view":[77],"experiences":[78],"using":[79],"TouchDesigner.":[80],"technology":[82],"has":[83],"potential":[85,120],"transform":[87],"wide":[89],"range":[90],"industries,":[92],"entertainment":[94],"gaming":[96],"architecture":[98],"design.":[100],"Overall,":[101],"this":[102],"presents":[104],"significant":[106],"contribution":[107],"field":[110],"generative":[112],"AI":[113],"computer":[115],"vision,":[116],"showcases":[118],"DepthFusion":[124],"revolutionize":[126],"content":[127],"creation":[128],"digital":[130],"experiences.":[131],"A":[132],"short":[133],"video":[134],"summarizing":[135],"approach":[137],"can":[138],"be":[139],"found":[140],"at":[141],"https://t.ly/tdi2.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}