TY - GEN
T1 - Fourier Feature Activated Neural-field Modelling For Human Avatar Representation
AU - Yang, Qing
AU - Weng, Dongdong
AU - Zhang, Hua
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In this paper, we introduce a novel neural representation method called Fourier Feature Activated Neural-field Modelling (FFANM) for 3D models. FFANM is designed to accurately and efficiently capture the surface geometry of 4D human avatars, which has numerous applications in the fields of remote conferencing, livestreaming marketing, short video web-cast, VR/AR, and video games and movie industry. While existing neural modelling methods are capable of representing either low-frequency or high-frequency surface geometry, they cannot do so simultaneously, resulting in poor overall representation quality. To address this limitation, we propose FFANM, which incorporates position encoding and periodic activation to leverage its Fourier properties for better representation of high-frequency information, while maintaining smooth surfaces free from noise. Our experiments demonstrate that FFANM outperforms state-of-the-art methods both quantitatively and qualitatively in terms of overall model reconstruction quality and high-frequency geometry details representation. Finally, We apply our proposed method, FFANM, in the 4D human avatar digitization pipeline and Metaverse application, and its superior visual performance demonstrates its capability in dynamic scenarios.
AB - In this paper, we introduce a novel neural representation method called Fourier Feature Activated Neural-field Modelling (FFANM) for 3D models. FFANM is designed to accurately and efficiently capture the surface geometry of 4D human avatars, which has numerous applications in the fields of remote conferencing, livestreaming marketing, short video web-cast, VR/AR, and video games and movie industry. While existing neural modelling methods are capable of representing either low-frequency or high-frequency surface geometry, they cannot do so simultaneously, resulting in poor overall representation quality. To address this limitation, we propose FFANM, which incorporates position encoding and periodic activation to leverage its Fourier properties for better representation of high-frequency information, while maintaining smooth surfaces free from noise. Our experiments demonstrate that FFANM outperforms state-of-the-art methods both quantitatively and qualitatively in terms of overall model reconstruction quality and high-frequency geometry details representation. Finally, We apply our proposed method, FFANM, in the 4D human avatar digitization pipeline and Metaverse application, and its superior visual performance demonstrates its capability in dynamic scenarios.
KW - 3D model
KW - Implicit Model
KW - Neural Fields
KW - Neural Representations
UR - http://www.scopus.com/inward/record.url?scp=85187363650&partnerID=8YFLogxK
U2 - 10.1109/SWC57546.2023.10449023
DO - 10.1109/SWC57546.2023.10449023
M3 - Conference contribution
AN - SCOPUS:85187363650
T3 - Proceedings - 2023 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Autonomous and Trusted Vehicles, Scalable Computing and Communications, Digital Twin, Privacy Computing and Data Security, Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PCDS/Metaverse 2023
BT - Proceedings - 2023 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Autonomous and Trusted Vehicles, Scalable Computing and Communications, Digital Twin, Privacy Computing and Data Security, Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PCDS/Metaverse 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th IEEE Smart World Congress, SWC 2023
Y2 - 28 August 2023 through 31 August 2023
ER -