Can I read 3D facial expression retargeting framework based on an identity-independent expression feature vector on EtoBox?

3D facial expression retargeting framework based on an identity-independent expression feature vector by Ziqi Tu; Dongdong Weng; Bin Liang; Le Luo is a Computer Science article available to read on EtoBox.

What is 3D facial expression retargeting framework based on an identity-independent expression feature vector about?

One important aspect of multimedia application scenarios is the ability to control the facial expressions of virtual characters. One popular solution is to retarget the expressions of actors to virtual characters. Traditional 3D facial expression retargeting algorithms are mostly based on the Blendshape model. However, excessive reliance on the Blendshape model introduces several limitations. For example, the quality of the base expressions has a large influence on the expression retargeting results, requires large amounts of 3D face data, and must be calibrated for each user. We propose a 3D facial expression retargeting framework based on an identity-independent expression feature vector (hereafter referred to as the expression vector). This expression vector, which is related only to facial expressions, is originally extracted from face images; then, the corresponding expressions are transferred to the target (which can be any 3D face model) using V2ENet, a generative adversarial network (GAN)-structured model. Our framework requires only the expression vector and a neutral 3D face model to achieve natural and vivid expression retargeting, and it does not rely on the Blendshape

Who reads 3D facial expression retargeting framework based on an identity-independent expression feature vector?

Author

Ziqi Tu; Dongdong Weng; Bin Liang; Le Luo

Publisher

Springer Science and Business Media LLC

Published

2023

Language

EN

Field

Computer Science (Physical Sciences)