Enhancing Facial Reconstruction Using Graph Attention Networks

Enhancing Facial Reconstruction Using Graph Attention Networks

Traditionally, research on three-dimensional (3D) facial reconstruction has focused heavily on methods that use 3D Morphable Models (3DMMs) based on principal component analysis (PCA). Because such methods are linear, they are robust to external noise. The PCA method has limitations when restoring f...

Full description

Bibliographic Details
Main Authors: Hyeong Geun Lee, Jee Sic Hur, Yeo Chan Yoon, Soo Kyun Kim
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Graph convolution network
graph attention network
convolution neural network
variational autoencoder
facial reconstruction
Online Access:https://ieeexplore.ieee.org/document/10339317/

Internet

https://ieeexplore.ieee.org/document/10339317/

Similar Items