{"id":"https://openalex.org/W4416150643","doi":"https://doi.org/10.1109/iccv51701.2025.01124","title":"Avat3r: Large Animatable Gaussian Reconstruction Model for High-Fidelity 3D Head Avatars","display_name":"Avat3r: Large Animatable Gaussian Reconstruction Model for High-Fidelity 3D Head Avatars","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416150643","doi":"https://doi.org/10.1109/iccv51701.2025.01124"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01124","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/2502.20220","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048779944","display_name":"Tobias Kirschstein","orcid":"https://orcid.org/0009-0002-5308-591X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Kirschstein","raw_affiliation_strings":["Technical University of Munich1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich1","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101750673","display_name":"Javier Romero","orcid":"https://orcid.org/0000-0001-5841-0166"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Javier Romero","raw_affiliation_strings":["Technical University of Munich1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich1","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027219028","display_name":"Artem Sevastopolsky","orcid":"https://orcid.org/0000-0003-2951-1448"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Artem Sevastopolsky","raw_affiliation_strings":["Technical University of Munich1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich1","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088583491","display_name":"Matthias Nie\u00dfner","orcid":"https://orcid.org/0000-0001-6093-5199"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Nie\u00dfner","raw_affiliation_strings":["Technical University of Munich1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich1","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102959646","display_name":"Shunsuke Saito","orcid":"https://orcid.org/0000-0003-2053-3472"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shunsuke Saito","raw_affiliation_strings":["Meta Reality Labs Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Pittsburgh","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"12089","last_page":"12100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8907999992370605,"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/T11448","display_name":"Face recognition and analysis","score":0.8907999992370605,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05810000002384186,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.006500000134110451,"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/robustness","display_name":"Robustness (evolution)","score":0.5432000160217285},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.5044999718666077},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.4790000021457672},{"id":"https://openalex.org/keywords/human-head","display_name":"Human head","score":0.4690999984741211},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.4106000065803528},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4065999984741211},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35760000348091125},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821999788284302},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6714000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6460999846458435},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5432000160217285},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C2780549717","wikidata":"https://www.wikidata.org/wiki/Q3409626","display_name":"Human head","level":3,"score":0.4690999984741211},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2781089380","wikidata":"https://www.wikidata.org/wiki/Q5936753","display_name":"Human-body model","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C9751117","wikidata":"https://www.wikidata.org/wiki/Q17105103","display_name":"Optical head-mounted display","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01124","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:2502.20220","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20220","pdf_url":"https://arxiv.org/pdf/2502.20220","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.2502.20220","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.20220","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":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:2502.20220","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.20220","pdf_url":"https://arxiv.org/pdf/2502.20220","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":{"Traditionally,":[0],"creating":[1,196],"photo-realistic":[2],"3D":[3,44,73,84,106,142,197],"head":[4,45,85,143,198],"avatars":[5,144,199],"requires":[6],"a":[7,40,49,69,77,159,180],"studio-level":[8],"multi-view":[9,79],"capture":[10,152],"setup":[11],"and":[12,42,67,93,171,174,209],"expensive":[13],"optimization":[14],"during":[15,57,136],"test-time,":[16],"limiting":[17],"the":[18,25,98,105,139,189],"use":[19],"of":[20,141,192,202],"digital":[21],"human":[22,74,99],"doubles":[23],"to":[24,115,133],"VFX":[26],"industry":[27],"or":[28,156],"offline":[29],"renderings.":[30],"To":[31,103],"address":[32],"this":[33],"shortcoming,":[34],"we":[35,61,87,123,187],"present":[36],"Avat3r,":[37],"which":[38],"regresses":[39],"high-quality":[41],"animatable":[43,66],"avatar":[46],"from":[47,76,91,97,145,158,200],"just":[48],"few":[50],"input":[51,128],"images,":[52,208],"vastly":[53],"reducing":[54],"compute":[55],"requirements":[56],"inference.":[58],"More":[59],"specifically,":[60],"make":[62],"Large":[63],"Reconstruction":[64],"Models":[65],"learn":[68],"powerful":[70],"prior":[71],"over":[72],"heads":[75],"large":[78],"video":[80],"dataset.":[81],"For":[82],"better":[83],"reconstructions,":[86],"employ":[88],"position":[89],"maps":[90,96],"DUSt3R":[92],"generalized":[94],"feature":[95],"foundation":[100],"model":[101,135],"Sapiens.":[102],"animate":[104],"head,":[107],"our":[108,134,177,193],"key":[109],"discovery":[110],"is":[111,119],"that":[112,176],"simple":[113],"cross-attention":[114],"an":[116,149],"expression":[117],"code":[118],"already":[120],"sufficient.":[121],"Finally,":[122,186],"increase":[124],"robustness":[125],"by":[126],"feeding":[127],"images":[129,201],"with":[130,153,165],"different":[131,203],"expressions":[132],"training,":[137],"enabling":[138],"reconstruction":[140],"inconsistent":[146],"inputs,":[147],"e.g.,":[148],"imperfect":[150],"phone":[151],"accidental":[154],"movement,":[155],"frames":[157],"monocular":[160],"video.":[161],"We":[162],"compare":[163],"Avat3r":[164],"current":[166],"state-of-the-art":[167],"methods":[168],"for":[169],"few-input":[170],"single-input":[172],"scenarios,":[173],"find":[175],"method":[178],"has":[179],"competitive":[181],"advantage":[182],"in":[183],"both":[184],"tasks.":[185],"demonstrate":[188],"wide":[190],"applicability":[191],"proposed":[194],"model,":[195],"sources,":[204],"smartphone":[205],"captures,":[206],"single":[207],"even":[210],"out-of-domain":[211],"inputs":[212],"like":[213],"antique":[214],"busts.":[215],"Project":[216],"website:":[217],"https://tobias-kirschstein.github.io/avat3r/":[218]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}