Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Landmark Guided 4D Facial Expression Generation

Xin Lu, Zhengda Lu, Yiqun Wang, Jun Xiao

TL;DR

A generative model that learns to synthesize the 4D facial expression with the neutral landmark while adding an identity discriminator and a landmark autoencoder to the basic WGAN for achieving better identity robustness.

Abstract

In this paper, we proposed a generative model that learns to synthesize the 4D facial expression with the neutral landmark. Existing works mainly focus on the generation of sequences guided by expression labels, speech, etc, while they are not robust to the change of different identities. Our LM-4DGAN utilizes neutral landmarks to guide the facial expression generation while adding an identity discriminator and a landmark autoencoder to the basic WGAN for achieving better identity robustness. Furthermore, we add a cross-attention mechanism to the existing displacement decoder which is suitable for the given identity.

Landmark Guided 4D Facial Expression Generation

TL;DR

A generative model that learns to synthesize the 4D facial expression with the neutral landmark while adding an identity discriminator and a landmark autoencoder to the basic WGAN for achieving better identity robustness.

Abstract

In this paper, we proposed a generative model that learns to synthesize the 4D facial expression with the neutral landmark. Existing works mainly focus on the generation of sequences guided by expression labels, speech, etc, while they are not robust to the change of different identities. Our LM-4DGAN utilizes neutral landmarks to guide the facial expression generation while adding an identity discriminator and a landmark autoencoder to the basic WGAN for achieving better identity robustness. Furthermore, we add a cross-attention mechanism to the existing displacement decoder which is suitable for the given identity.
Paper Structure (4 sections, 2 equations, 1 figure, 1 table)

This paper contains 4 sections, 2 equations, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Our approach
  3. EXPERIMENTS AND RESULTS
  4. Conclusion

Figures (1)

  • Figure 1: Qualitative results. The first line is the ground truth of the expression mouth-extreme with different identities. The second line is the generating results of Motion3D while the third line is the generating results of our network.