{"id":"https://openalex.org/W4389599076","doi":"https://doi.org/10.48550/arxiv.2312.04651","title":"VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment","display_name":"VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment","publication_year":2023,"publication_date":"2023-12-07","ids":{"openalex":"https://openalex.org/W4389599076","doi":"https://doi.org/10.48550/arxiv.2312.04651"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.04651","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.04651","pdf_url":"https://arxiv.org/pdf/2312.04651","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.04651","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053502794","display_name":"Phong A. Tran","orcid":"https://orcid.org/0000-0003-2820-7399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Phong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072400499","display_name":"Egor Zakharov","orcid":"https://orcid.org/0000-0002-9880-9531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zakharov, Egor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045616447","display_name":"Long-Nhat Ho","orcid":"https://orcid.org/0009-0006-5911-8945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ho, Long-Nhat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tran, Anh Tuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Anh Tuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000484166","display_name":"Liwen Hu","orcid":"https://orcid.org/0000-0002-0257-5292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Liwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100348498","display_name":"Hao Li","orcid":"https://orcid.org/0000-0001-7915-582X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9897000193595886,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9897000193595886,"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/T11448","display_name":"Face recognition and analysis","score":0.9896000027656555,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9768999814987183,"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":0.8616067171096802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6303309798240662},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5494533777236938},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.5312530398368835},{"id":"https://openalex.org/keywords/radiance","display_name":"Radiance","score":0.4994471073150635},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4913589060306549},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4533518850803375},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42435818910598755},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.41102659702301025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3342670202255249},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.21672216057777405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8616067171096802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6303309798240662},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5494533777236938},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.5312530398368835},{"id":"https://openalex.org/C23690007","wikidata":"https://www.wikidata.org/wiki/Q1411145","display_name":"Radiance","level":2,"score":0.4994471073150635},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4913589060306549},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4533518850803375},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42435818910598755},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.41102659702301025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3342670202255249},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.21672216057777405},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.04651","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.04651","pdf_url":"https://arxiv.org/pdf/2312.04651","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2312.04651","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.04651","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.04651","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.04651","pdf_url":"https://arxiv.org/pdf/2312.04651","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W3006162251"],"abstract_inverted_index":{"We":[0,152,165,186],"present":[1],"a":[2,10,81,103,119,160,168,191],"3D-aware":[3,43,200],"one-shot":[4],"head":[5,201,211],"reenactment":[6,44,84,202],"method":[7,23],"based":[8,37,124],"on":[9,38,66,125,159,190,203],"fully":[11],"volumetric":[12,122],"neural":[13,48,104,149],"disentanglement":[14,76,106,155],"framework":[15],"for":[16,33,216],"source":[17,112,218],"appearance":[18,57],"and":[19,26,29,114,142,196,206,213,219],"driver":[20,92,115],"expressions.":[21,79,96],"Our":[22],"is":[24],"real-time":[25],"produces":[27],"high-fidelity":[28],"view-consistent":[30,56],"output,":[31],"suitable":[32],"3D":[34,52,121,179],"teleconferencing":[35],"systems":[36],"holographic":[39],"displays.":[40],"Existing":[41],"cutting-edge":[42],"methods":[45],"often":[46,86],"use":[47],"radiance":[49,150],"fields":[50],"or":[51,93],"meshes":[53],"to":[54,73,173],"produce":[55],"encoding,":[58],"but,":[59],"at":[60],"the":[61,91,111,139,175,178,182],"same":[62,183],"time,":[63],"they":[64],"rely":[65],"linear":[67],"face":[68],"models,":[69],"such":[70],"as":[71],"3DMM,":[72],"achieve":[74,153],"its":[75],"with":[77,134],"facial":[78],"As":[80],"result,":[82],"their":[83],"results":[85],"exhibit":[87],"identity":[88],"leakage":[89],"from":[90,138,144],"have":[94],"unnatural":[95],"To":[97],"address":[98],"these":[99],"problems,":[100],"we":[101],"propose":[102],"self-supervised":[105,157],"approach":[107,172],"that":[108],"lifts":[109],"both":[110,217],"image":[113],"video":[116,163],"frame":[117],"into":[118],"shared":[120],"representation":[123,128],"tri-planes.":[126],"This":[127],"can":[129],"then":[130],"be":[131],"freely":[132],"manipulated":[133],"expression":[135],"tri-planes":[136],"extracted":[137],"driving":[140],"images":[141],"rendered":[143],"an":[145],"arbitrary":[146],"view":[147],"using":[148,181],"fields.":[151],"this":[154],"via":[156],"learning":[158],"large":[161],"in-the-wild":[162],"dataset.":[164],"further":[166],"introduce":[167],"highly":[169,204],"effective":[170],"fine-tuning":[171],"improve":[174],"generalizability":[176],"of":[177,194],"lifting":[180],"real-world":[184],"data.":[185],"demonstrate":[187],"state-of-the-art":[188],"performance":[189],"wide":[192],"range":[193],"datasets,":[195],"also":[197],"showcase":[198],"high-quality":[199],"challenging":[205],"diverse":[207],"subjects,":[208],"including":[209],"non-frontal":[210],"poses":[212],"complex":[214],"expressions":[215],"driver.":[220]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2023-12-12T00:00:00"}