{"id":"https://openalex.org/W7155225889","doi":"https://doi.org/10.48550/arxiv.2604.19702","title":"Face Anything: 4D Face Reconstruction from Any Image Sequence","display_name":"Face Anything: 4D Face Reconstruction from Any Image Sequence","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155225889","doi":"https://doi.org/10.48550/arxiv.2604.19702"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19702","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19702","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.19702","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047380305","display_name":"Umut Kocasar\u0131","orcid":"https://orcid.org/0000-0002-6492-3790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kocasari, Umut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018692382","display_name":"Simon Giebenhain","orcid":"https://orcid.org/0000-0002-7588-8767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giebenhain, Simon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103118864","display_name":"Richard Shaw","orcid":"https://orcid.org/0000-0002-3141-5562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaw, Richard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134299214","display_name":"Matthias Nie\u00dfner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie\u00dfner, Matthias","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/T11448","display_name":"Face recognition and analysis","score":0.9753000140190125,"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":0.9753000140190125,"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":0.004800000227987766,"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/T10057","display_name":"Face and Expression Recognition","score":0.0024999999441206455,"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/canonical-correlation","display_name":"Canonical correlation","score":0.5418999791145325},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5367000102996826},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4763000011444092},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.4404999911785126},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.41589999198913574},{"id":"https://openalex.org/keywords/canonical-form","display_name":"Canonical form","score":0.39989998936653137},{"id":"https://openalex.org/keywords/correspondence-problem","display_name":"Correspondence problem","score":0.39899998903274536},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.39259999990463257},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.39160001277923584}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.756600022315979},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6984999775886536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5590000152587891},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4018999934196472},{"id":"https://openalex.org/C204707403","wikidata":"https://www.wikidata.org/wiki/Q1152398","display_name":"Canonical form","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C3004257","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Correspondence problem","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3885999917984009},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C20885615","wikidata":"https://www.wikidata.org/wiki/Q825595","display_name":"Surface reconstruction","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C129641003","wikidata":"https://www.wikidata.org/wiki/Q267189","display_name":"Active shape model","level":3,"score":0.35010001063346863},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C2780427248","wikidata":"https://www.wikidata.org/wiki/Q17014996","display_name":"Fundamental matrix (linear differential equation)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C54654163","wikidata":"https://www.wikidata.org/wiki/Q5428359","display_name":"Face hallucination","level":5,"score":0.2671999931335449},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2621000111103058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19702","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19702","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":"doi:10.48550/arxiv.2604.19702","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19702","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5423315167427063}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"reconstruction":[1,40,69,73,154,170],"and":[2,18,28,67,79,91,106,127,147,155,164],"tracking":[3,66,110,156],"of":[4],"dynamic":[5,68,169],"human":[6],"faces":[7],"from":[8],"image":[9,146],"sequences":[10],"is":[11],"challenging":[12],"because":[13],"non-rigid":[14],"deformations,":[15],"expression":[16],"changes,":[17],"viewpoint":[19],"variations":[20],"occur":[21],"simultaneously,":[22],"creating":[23],"significant":[24],"ambiguity":[25],"in":[26,57],"geometry":[27,78,134],"correspondence":[29,162],"estimation.":[30],"We":[31,115],"present":[32],"a":[33,47,53,58,71,83,112,120],"unified":[34,190],"method":[35,95],"for":[36,189],"high-fidelity":[37],"4D":[38,192],"facial":[39,44,55,108,129,182,193],"based":[41],"on":[42,145],"canonical":[43,60,72,92,128,141,181],"point":[45,109,183],"prediction,":[46],"representation":[48],"that":[49,123,136],"assigns":[50],"each":[51],"pixel":[52],"normalized":[54],"coordinate":[56],"shared":[59],"space.":[61,142],"This":[62],"formulation":[63,118],"transforms":[64],"dense":[65,103],"into":[70,139],"problem,":[74],"enabling":[75],"temporally":[76,100],"consistent":[77],"reliable":[80],"correspondences":[81],"within":[82,111],"single":[84,113],"feed-forward":[85,191],"model.":[86],"By":[87],"jointly":[88,124],"predicting":[89],"depth":[90,98,126,174],"coordinates,":[93,130],"our":[94],"enables":[96],"accurate":[97],"estimation,":[99],"stable":[101],"reconstruction,":[102],"3D":[104],"geometry,":[105],"robust":[107],"architecture.":[114],"implement":[116],"this":[117],"using":[119,132],"transformer-based":[121],"model":[122],"predicts":[125],"trained":[131],"multi-view":[133],"data":[135],"non-rigidly":[137],"warps":[138],"the":[140],"Extensive":[143],"experiments":[144],"video":[148],"benchmarks":[149],"demonstrate":[150],"state-of-the-art":[151],"performance":[152],"across":[153],"tasks,":[157],"achieving":[158],"approximately":[159],"3$\\times$":[160],"lower":[161],"error":[163],"faster":[165],"inference":[166],"than":[167],"prior":[168],"methods,":[171],"while":[172],"improving":[173],"accuracy":[175],"by":[176],"16%.":[177],"These":[178],"results":[179],"highlight":[180],"prediction":[184],"as":[185],"an":[186],"effective":[187],"foundation":[188],"reconstruction.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-23T00:00:00"}