FC-4DFS: Frequency-controlled Flexible 4D Facial Expression Synthesizing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917331530153984 |
|---|---|
| author | Lu, Xin Lu, Chuanqing Zhuang. Zhengda Wang, Yiqun Xiao, Jun |
| author_facet | Lu, Xin Lu, Chuanqing Zhuang. Zhengda Wang, Yiqun Xiao, Jun |
| contents | 4D facial expression synthesizing is a critical problem in the fields of computer vision and graphics. Current methods lack flexibility and smoothness when simulating the inter-frame motion of expression sequences. In this paper, we propose a frequency-controlled 4D facial expression synthesizing method, FC-4DFS. Specifically, we introduce a frequency-controlled LSTM network to generate 4D facial expression sequences frame by frame from a given neutral landmark with a given length. Meanwhile, we propose a temporal coherence loss to enhance the perception of temporal sequence motion and improve the accuracy of relative displacements. Furthermore, we designed a Multi-level Identity-Aware Displacement Network based on a cross-attention mechanism to reconstruct the 4D facial expression sequences from landmark sequences. Finally, our FC-4DFS achieves flexible and SOTA generation results of 4D facial expression sequences with different lengths on CoMA and Florence4D datasets. The code will be available on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10326 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FC-4DFS: Frequency-controlled Flexible 4D Facial Expression Synthesizing Lu, Xin Lu, Chuanqing Zhuang. Zhengda Wang, Yiqun Xiao, Jun Graphics 4D facial expression synthesizing is a critical problem in the fields of computer vision and graphics. Current methods lack flexibility and smoothness when simulating the inter-frame motion of expression sequences. In this paper, we propose a frequency-controlled 4D facial expression synthesizing method, FC-4DFS. Specifically, we introduce a frequency-controlled LSTM network to generate 4D facial expression sequences frame by frame from a given neutral landmark with a given length. Meanwhile, we propose a temporal coherence loss to enhance the perception of temporal sequence motion and improve the accuracy of relative displacements. Furthermore, we designed a Multi-level Identity-Aware Displacement Network based on a cross-attention mechanism to reconstruct the 4D facial expression sequences from landmark sequences. Finally, our FC-4DFS achieves flexible and SOTA generation results of 4D facial expression sequences with different lengths on CoMA and Florence4D datasets. The code will be available on GitHub. |
| title | FC-4DFS: Frequency-controlled Flexible 4D Facial Expression Synthesizing |
| topic | Graphics |
| url | https://arxiv.org/abs/2603.10326 |