Presentation / Installation


NOFA: NeRF-based One-shot Facial Avatar Reconstruction
SessionNeRFs for Avatars
DescriptionWe propose a one-shot 3D facial avatar reconstruction framework. It leverages an efficient encoder-decoder network along with a compensation network to reconstruct the canonical neural volume of the input image and a 3DMM-based deformation field to model facial dynamics. We conduct extensive experiments and demonstrate our superior performance.
Authors
Wangbo Yu
Tencent AI Lab
Yanbo Fan
Tencent AI Lab
Yong Zhang
Tencent AI Lab
Xuan Wang
Ant Group
Fei Yin
Tsinghua Shenzhen International Graduate School,Tsinghua University
Yunpeng Bai
Tsinghua Shenzhen International Graduate School,Tsinghua University
Yan-Pei Cao
Tencent AI Lab
Ying Shan
Tencent AI Lab
Yang Wu
Tencent AI Lab
Zhongqian Sun
Tencent AI Lab
Baoyuan Wu
The Chinese University of Hong Kong,Shenzhen
Event Type
Technical Paper
TimeThursday, 10 August 20234:29pm - 4:39pm PDT
LocationPetree Hall C
ACM Digital Library Technical Paper PDF
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Thursday, 10 August 20233:45pm - 5:15pm PDTPetree Hall C
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Rendering
Video
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar