Landmark Guided 4D Facial Expression Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Xin, Lu, Zhengda, Wang, Yiqun, Xiao, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908878217674752
author Lu, Xin
Lu, Zhengda
Wang, Yiqun
Xiao, Jun
author_facet Lu, Xin
Lu, Zhengda
Wang, Yiqun
Xiao, Jun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10337
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Landmark Guided 4D Facial Expression Generation
Lu, Xin
Lu, Zhengda
Wang, Yiqun
Xiao, Jun
Graphics
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.
title Landmark Guided 4D Facial Expression Generation
topic Graphics
url https://arxiv.org/abs/2603.10337