HeadNeRF: A Realtime NeRF-based Parametric Head Model

In this paper, we propose HeadNeRF, a novel NeRF-based parametric head model that integrates the neural radiance field to the parametric representation of the human head. It can render high fidelity head images in real-time on modern GPUs, and supports directly controlling the generated images'...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 20342 - 20352
Hauptverfasser: Hong, Yang, Peng, Bo, Xiao, Haiyao, Liu, Ligang, Zhang, Juyong
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2022
Schlagworte:
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In this paper, we propose HeadNeRF, a novel NeRF-based parametric head model that integrates the neural radiance field to the parametric representation of the human head. It can render high fidelity head images in real-time on modern GPUs, and supports directly controlling the generated images' rendering pose and various semantic attributes. Different from existing related parametric models, we use the neural radiance fields as a novel 3D proxy instead of the traditional 3D textured mesh, which makes that HeadNeRF is able to generate high fidelity images. However, the computationally expensive rendering process of the original NeRF hinders the construction of the parametric NeRF model. To address this issue, we adopt the strategy of integrating 2D neural rendering to the rendering process of NeRF and design novel loss terms. As a result, the rendering speed of HeadNeRF can be significantly accelerated, and the rendering time of one frame is reduced from 5s to 25ms. The well designed loss terms also improve the rendering accuracy, and the fine-level details of the human head, such as the gaps between teeth, wrinkles, and beards, can be represented and synthesized by HeadNeRF. Extensive experimental results and several applications demonstrate its effectiveness. The trained parametric model is available at https://github.com/CrisHY1995/headnerf.
AbstractList In this paper, we propose HeadNeRF, a novel NeRF-based parametric head model that integrates the neural radiance field to the parametric representation of the human head. It can render high fidelity head images in real-time on modern GPUs, and supports directly controlling the generated images' rendering pose and various semantic attributes. Different from existing related parametric models, we use the neural radiance fields as a novel 3D proxy instead of the traditional 3D textured mesh, which makes that HeadNeRF is able to generate high fidelity images. However, the computationally expensive rendering process of the original NeRF hinders the construction of the parametric NeRF model. To address this issue, we adopt the strategy of integrating 2D neural rendering to the rendering process of NeRF and design novel loss terms. As a result, the rendering speed of HeadNeRF can be significantly accelerated, and the rendering time of one frame is reduced from 5s to 25ms. The well designed loss terms also improve the rendering accuracy, and the fine-level details of the human head, such as the gaps between teeth, wrinkles, and beards, can be represented and synthesized by HeadNeRF. Extensive experimental results and several applications demonstrate its effectiveness. The trained parametric model is available at https://github.com/CrisHY1995/headnerf.
Author Liu, Ligang
Xiao, Haiyao
Hong, Yang
Peng, Bo
Zhang, Juyong
Author_xml – sequence: 1
  givenname: Yang
  surname: Hong
  fullname: Hong, Yang
  email: hymath@mail.ustc.edu.cn
  organization: University of Science and Technology of China
– sequence: 2
  givenname: Bo
  surname: Peng
  fullname: Peng, Bo
  email: pb15881461858@mail.ustc.edu.cn
  organization: University of Science and Technology of China
– sequence: 3
  givenname: Haiyao
  surname: Xiao
  fullname: Xiao, Haiyao
  email: xhy1999512@mail.ustc.edu.cn
  organization: University of Science and Technology of China
– sequence: 4
  givenname: Ligang
  surname: Liu
  fullname: Liu, Ligang
  email: lgliu@ustc.edu.cn
  organization: University of Science and Technology of China
– sequence: 5
  givenname: Juyong
  surname: Zhang
  fullname: Zhang, Juyong
  email: juyong@ustc.edu.cn
  organization: University of Science and Technology of China
BookMark eNotjMFKw0AQQFdRsK39Aj3sDyTO7G4mu95KsFaoWoJ6LZPsBCJJK0ku_r0WPT14PN5cXRyOB1HqFiFFhHBXfOzKzJD3qQFjUsCQ2zM1R6LMUXBkz9UMgWxCAcOVWo7jJwBYg0jBz1S2EY4vUq7v9UqXwt3U9qJPIql4lKh3PHAv09DW-pTq52OU7lpdNtyNsvznQr2vH96KTbJ9fXwqVtukRfRTUjsCiD6vvM8bE9k1woDETsg0hoNU8ZeGTDTBUu1iJXXjMIbG-5ixtwt18_dtRWT_NbQ9D9_74D1YF-wPn09Gtw
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52688.2022.01973
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 Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665469463
9781665469463
EISSN 1063-6919
EndPage 20352
ExternalDocumentID 9880349
Genre orig-research
GrantInformation_xml – fundername: National Key R&D Program of China
  grantid: 2020YFC1523102
  funderid: 10.13039/501100012166
– fundername: Fundamental Research Funds for the Central Universities
  grantid: WK3470000021
  funderid: 10.13039/501100012226
– fundername: National Natural Science Foundation of China
  grantid: 62122071,62025207
  funderid: 10.13039/501100001809
– fundername: Youth Innovation Promotion Association CAS
  grantid: 2018495
  funderid: 10.13039/501100004739
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-i118t-c4600d87b887f2da4fea016a4e62f2a9ebd2f2262d2936c4dbecf41d9f88d5a83
IEDL.DBID RIE
IngestDate Wed Aug 27 02:15:09 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-c4600d87b887f2da4fea016a4e62f2a9ebd2f2262d2936c4dbecf41d9f88d5a83
PageCount 11
ParticipantIDs ieee_primary_9880349
PublicationCentury 2000
PublicationDate 2022-June
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: 2022-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.6395912
Snippet In this paper, we propose HeadNeRF, a novel NeRF-based parametric head model that integrates the neural radiance field to the parametric representation of the...
SourceID ieee
SourceType Publisher
StartPage 20342
SubjectTerms Computer vision
Ethics
Face and gestures; 3D from multi-view and sensors; 3D from single images; Representation learning; Vision + graphics
Head
Real-time systems
Rendering (computer graphics)
Semantics
Three-dimensional displays
Title HeadNeRF: A Realtime NeRF-based Parametric Head Model
URI https://ieeexplore.ieee.org/document/9880349
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09a8MwED2S0KFT2ial32joWCW2LOujWwkNGUowoQ3ZgmRJEGiTko_-_uock3bo0slGCAx3st-T_N4dwH0kITkvVUrTIBLKmc2oZUzSSEaFYi4CeOVynb7I8VjNZrpowMPBC-O9r8Rnvoe31b98typ3eFTW13GxZVw3oSml2Hu1DucpWdzJCK1qd1ya6P5gWkywmAkKuBjrRS6DzdF_9VCpIGTY_t_DT6D748UjxQFlTqHhl2fQrskjqV_NTQfyUczW2E-Gj-SJTFDVtfjwBAcoIpUjhUEdFhbkJziVYBe09y68DZ9fByNa90Sgi7gV2NKSR4bilLTx4xCYMzx4E1mb4V6wwIz21sUrE8xFHBcldzFHgadOB6VcblR2Dq3laukvgBjrEu4zl-CMoLRKpRHWeatcqYLML6GDUZh_7stezOsAXP09fA3HGOa9iuoGWtv1zt_CUfm1XWzWd1WuvgE6LpNf
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH7MKehp6ib-NgePZmvTNE28iTgmzlLGHLuNtElgoJvsh3-_eV2ZHrx4agmBwntpvy_p-94HcOtJSMwLGdLQiYBylkc0ZyyhnowKyYwH8FLlOuonaSrHY5XV4G6rhbHWlsVnto235b98My_WeFTWUX6xRVztwC46Z1Vqre2JSuT3MkLJSh8XBqrzOMoG2M4ES7gYa3s2g_bov1xUShDpNv73-ENo_ajxSLbFmSOo2dkxNCr6SKqXc9mEuOfzldpB9548kAHWdU0_LMEBilhlSKaxEgtb8hOcStAH7b0Fb92n4WOPVq4IdOo3AytacM9RjExy_3lwzGjurPa8TXMrmGNa2dz4KxPMeCQXBTc-S46HRjkpTaxldAL12XxmT4Ho3ATcRibAGU4qGSZa5Mbm0hTSJfEZNDEKk89N44tJFYDzv4dvYL83fO1P-s_pywUcYMg3NVWXUF8t1vYK9oqv1XS5uC7z9g0ZrZao
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%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=HeadNeRF%3A+A+Realtime+NeRF-based+Parametric+Head+Model&rft.au=Hong%2C+Yang&rft.au=Peng%2C+Bo&rft.au=Xiao%2C+Haiyao&rft.au=Liu%2C+Ligang&rft.date=2022-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=20342&rft.epage=20352&rft_id=info:doi/10.1109%2FCVPR52688.2022.01973&rft.externalDocID=9880349