Instant Volumetric Head Avatars
We present Instant Volumetric Head Avatars (INSTA), a novel approach for reconstructing photo-realistic digital avatars instantaneously. INSTA models a dynamic neural radiance field based on neural graphics primitives embedded around a parametric face model. Our pipeline is trained on a single monoc...
Gespeichert in:
| Veröffentlicht in: | Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 4574 - 4584 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Tagungsbericht |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
01.06.2023
|
| Schlagworte: | |
| ISSN: | 1063-6919 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | We present Instant Volumetric Head Avatars (INSTA), a novel approach for reconstructing photo-realistic digital avatars instantaneously. INSTA models a dynamic neural radiance field based on neural graphics primitives embedded around a parametric face model. Our pipeline is trained on a single monocular RGB portrait video that observes the subject under different expressions and views. While state-of-the-art methods take up to several days to train an avatar, our method can reconstruct a digital avatar in less than 10 minutes on modern GPU hardware, which is orders of magnitude faster than previous solutions. In addition, it allows for the interactive rendering of novel poses and expressions. By leveraging the geometry prior of the underlying parametric face model, we demonstrate that INSTA extrapolates to unseen poses. In quantitative and qualitative studies on various subjects, INSTA outperforms state-of-the-art methods regarding rendering quality and training time. Project website: https://zielon.github.io/insta/ |
|---|---|
| AbstractList | We present Instant Volumetric Head Avatars (INSTA), a novel approach for reconstructing photo-realistic digital avatars instantaneously. INSTA models a dynamic neural radiance field based on neural graphics primitives embedded around a parametric face model. Our pipeline is trained on a single monocular RGB portrait video that observes the subject under different expressions and views. While state-of-the-art methods take up to several days to train an avatar, our method can reconstruct a digital avatar in less than 10 minutes on modern GPU hardware, which is orders of magnitude faster than previous solutions. In addition, it allows for the interactive rendering of novel poses and expressions. By leveraging the geometry prior of the underlying parametric face model, we demonstrate that INSTA extrapolates to unseen poses. In quantitative and qualitative studies on various subjects, INSTA outperforms state-of-the-art methods regarding rendering quality and training time. Project website: https://zielon.github.io/insta/ |
| Author | Bolkart, Timo Zielonka, Wojciech Thies, Justus |
| Author_xml | – sequence: 1 givenname: Wojciech surname: Zielonka fullname: Zielonka, Wojciech email: wojciech.zielonka@tuebingen.mpg.de organization: Max Planck Institute for Intelligent Systems,Tübingen,Germany – sequence: 2 givenname: Timo surname: Bolkart fullname: Bolkart, Timo email: timo.bolkart@tuebingen.mpg.de organization: Max Planck Institute for Intelligent Systems,Tübingen,Germany – sequence: 3 givenname: Justus surname: Thies fullname: Thies, Justus email: justus.thies@tuebingen.mpg.de organization: Max Planck Institute for Intelligent Systems,Tübingen,Germany |
| BookMark | eNotzdFKwzAUgOEoCs7ZNxjYF2g9JydNTi5HUTcYKKK7HadpBpWtkyYKvr2CXv1333-tLsbTGJVaINSI4O_a7fNLo532tQZNNYAx5kwV3nmmBghQez5XMwRLlfXor1SR0jsAkEa0nmfqdj2mLGMut6fD5zHmaQjlKkpfLr8ky5Ru1OVeDikW_52rt4f713ZVbZ4e1-1yUw0aTK46_l2CEeLg2fTRBTRihUNEuw-kSYDRCpATZuN0tD1wIO6h65pgDM3V4s8dYoy7j2k4yvS9Q9BAiA39AFg9P8U |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CVPR52729.2023.00444 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISBN | 9798350301298 |
| EISSN | 1063-6919 |
| EndPage | 4584 |
| ExternalDocumentID | 10203115 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IH 6IL 6IN AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP OCL RIE RIL RIO |
| ID | FETCH-LOGICAL-i204t-b879804a38c984de7c14a6a8ce16fc323a0816a037a88472e6d08c38d0bb5c443 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 89 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001058542604087&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:56:31 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i204t-b879804a38c984de7c14a6a8ce16fc323a0816a037a88472e6d08c38d0bb5c443 |
| PageCount | 11 |
| ParticipantIDs | ieee_primary_10203115 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-June |
| PublicationDateYYYYMMDD | 2023-06-01 |
| PublicationDate_xml | – month: 06 year: 2023 text: 2023-June |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2023 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0003211698 |
| Score | 2.529491 |
| Snippet | We present Instant Volumetric Head Avatars (INSTA), a novel approach for reconstructing photo-realistic digital avatars instantaneously. INSTA models a dynamic... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 4574 |
| SubjectTerms | 3D from multi-view and sensors Avatars Face recognition Geometry Pipelines Telepresence Three-dimensional displays Training |
| Title | Instant Volumetric Head Avatars |
| URI | https://ieeexplore.ieee.org/document/10203115 |
| WOSCitedRecordID | wos001058542604087&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07b8IwED4V1KETfVD13QxdQ43t2M5YoSK6IFS1iA1dLrbEAhUEfj-2k1J16NDN8mLZJ9_L_r4P4Im0IhIZpt4tslQ6nXk_iFnKyTk0qgyk31FsQo_HZjbLJw1YPWJhrLXx85nthWF8yy9XtA2tMn_DOQvsMC1oaa1qsNahoSJ8KaNy08Dj-ix_Hkwn7xn32WMvaIT3IjXaLxGVGEOGnX-ufgrdHzReMjnEmTM4sstz6DTpY9Jczs0FPL7FVK9KptHjBOr9ZORNmLzssPL1axc-h68fg1Ha6B-kC85klRZG54ZJFIZyI0urqS9RoSHbV44EFxhUM5AJjcYHGW5VyQwJU7KiyEhKcQnt5WppryDxs84K4mRdIZ0rDc9RaObQFyxcWLyGbtjw_KumuJh_7_Xmj_lbOAlnWv-ZuoN2td7aezimXbXYrB-iYfa8Qo0I |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4omugJHxjf7MHrYmm72-7RGAlEJMQg4UZmZ9uECxhY-P22ZcV48OCt6aVpJ51X-30fwAOplEgkGDu3yGJpVeL8ICYxJ2tRp4Un_Q5iE2ow0JNJNqzA6gELY4wJn89Myw_DW36xoLVvlbkbzplnh9mHg0RKzrZwrV1LRbhiJs10BZBrs-zxeTx8T7jLH1teJbwVyNF-yaiEKNKp_3P9E2j84PGi4S7SnMKemZ9BvUogo-p6rs6h2QvJXhmNg8_x5PtR1xkxetpg6SrYBnx0XkbP3bhSQIhnnMkyzrXKNJMoNGVaFkZRW2KKmkw7tSS4QK-bgUwo1C7McJMWTJPQBcvzhKQUF1CbL-bmEiI3a40gTsbm0tpC8wyFYhZdycKFwSto-A1PP7ckF9PvvV7_Md-Eo-7orT_t9wavN3Dsz3f7g-oWauVybe7gkDblbLW8D0b6AkfNkE8 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Instant+Volumetric+Head+Avatars&rft.au=Zielonka%2C+Wojciech&rft.au=Bolkart%2C+Timo&rft.au=Thies%2C+Justus&rft.date=2023-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=4574&rft.epage=4584&rft_id=info:doi/10.1109%2FCVPR52729.2023.00444&rft.externalDocID=10203115 |