{"id":"https://openalex.org/W4416544220","doi":"https://doi.org/10.1109/iccv51701.2025.01314","title":"SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians","display_name":"SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416544220","doi":"https://doi.org/10.1109/iccv51701.2025.01314"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01314","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.12292","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025798902","display_name":"Liam Schoneveld","orcid":"https://orcid.org/0000-0002-7324-6234"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liam Schoneveld","raw_affiliation_strings":["Woven by Toyota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Woven by Toyota","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101813868","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0002-5153-4593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["Woven by Toyota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Woven by Toyota","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093427267","display_name":"Davide Davoli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093665","display_name":"Toyota Motor North America (United States)","ror":"https://ror.org/0076knn86","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093665","https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Davide Davoli","raw_affiliation_strings":["Toyota Motor Europe NV/SA associated partner by contracted service"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Motor Europe NV/SA associated partner by contracted service","institution_ids":["https://openalex.org/I4210093665"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015737161","display_name":"Jiapeng Tang","orcid":"https://orcid.org/0009-0000-2939-0055"},"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":"Jiapeng Tang","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Saimon Terazawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saimon Terazawa","raw_affiliation_strings":["Woven by Toyota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Woven by Toyota","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034253077","display_name":"Ko Nishino","orcid":"https://orcid.org/0000-0002-3534-3447"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ko Nishino","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","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 Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31641146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14162","last_page":"14172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9520999789237976,"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":0.9520999789237976,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.017899999395012856,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.010099999606609344,"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/monocular","display_name":"Monocular","score":0.6319000124931335},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5957000255584717},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5586000084877014},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5139999985694885},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5094000101089478},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.46239998936653137},{"id":"https://openalex.org/keywords/geometric-primitive","display_name":"Geometric primitive","score":0.4023999869823456},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3880000114440918}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7559000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289999723434448},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6319000124931335},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5914999842643738},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2644999921321869}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01314","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:2504.12292","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.12292","pdf_url":"https://arxiv.org/pdf/2504.12292","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.12292","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.12292","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.12292","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.12292","pdf_url":"https://arxiv.org/pdf/2504.12292","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416544220.pdf","grobid_xml":"https://content.openalex.org/works/W4416544220.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate,":[0],"real-time":[1],"3D":[2,17],"reconstruction":[3],"of":[4,47,84,127],"human":[5],"heads":[6],"from":[7,34],"monocular":[8],"images":[9],"and":[10,81,104,112,152],"videos":[11,37],"underlies":[12],"numerous":[13],"visual":[14],"applications.":[15],"As":[16],"ground":[18],"truth":[19],"data":[20],"is":[21,52],"hard":[22],"to":[23,32,89,99,108],"come":[24],"by":[25],"at":[26],"scale,":[27],"previous":[28],"methods":[29],"have":[30],"sought":[31],"learn":[33],"abundant":[35],"2D":[36,70,134],"in":[38,142,168],"a":[39,73,78,82,101,153],"self-supervised":[40,129,140],"manner.":[41],"Typically,":[42],"this":[43,90,95,128],"involves":[44],"the":[45,110,125,146],"use":[46],"differentiable":[48],"mesh":[49,80],"rendering,":[50],"which":[51],"effective":[53],"but":[54],"faces":[55,151],"limitations.":[56],"To":[57],"improve":[58],"on":[59,133,145],"this,":[60],"we":[61,76],"propose":[62],"SHeaP":[63],"(Self-supervised":[64],"Head":[65],"Geometry":[66],"Predictor":[67],"Learned":[68],"via":[69],"Gaussians).":[71],"Given":[72],"source":[74],"image,":[75],"predict":[77],"3DMM":[79,111],"set":[83],"Gaussians":[85,120],"that":[86,118],"are":[87],"rigged":[88,96],"mesh.":[91],"We":[92,116],"then":[93],"reanimate":[94],"head":[97],"avatar":[98],"match":[100],"target":[102],"frame,":[103],"backpropagate":[105],"photometric":[106],"losses":[107],"both":[109],"Gaussian":[113],"prediction":[114],"networks.":[115],"find":[117],"using":[119],"for":[121,149,156],"rendering":[122],"substantially":[123],"improves":[124],"effectiveness":[126],"approach.":[130],"Training":[131],"solely":[132],"data,":[135],"our":[136],"method":[137,160],"surpasses":[138],"existing":[139],"approaches":[141],"geometric":[143],"evaluations":[144],"NoW":[147],"benchmark":[148,155],"neutral":[150],"new":[154],"non-neutral":[157],"expressions.":[158],"Our":[159],"also":[161],"produces":[162],"highly":[163],"expressive":[164],"meshes,":[165],"outperforming":[166],"state-of-the-art":[167],"emotion":[169],"classification.":[170]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}