Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.14477 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917279459966976 |
|---|---|
| author | Zhang, Dong Peng, Jingwei Jiao, Yuyang Gu, Jiayuan Yu, Jingyi Chen, Jiahao |
| author_facet | Zhang, Dong Peng, Jingwei Jiao, Yuyang Gu, Jiayuan Yu, Jingyi Chen, Jiahao |
| contents | This paper presents a novel Expressive Facial Control (ExFace) method based on Diffusion Transformers, which achieves precise mapping from human facial blendshapes to bionic robot motor control. By incorporating an innovative model bootstrap training strategy, our approach not only generates high-quality facial expressions but also significantly improves accuracy and smoothness. Experimental results demonstrate that the proposed method outperforms previous methods in terms of accuracy, frame per second (FPS), and response time. Furthermore, we develop the ExFace dataset driven by human facial data. ExFace shows excellent real-time performance and natural expression rendering in applications such as robot performances and human-robot interactions, offering a new solution for bionic robot interaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14477 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ExFace: Expressive Facial Control for Humanoid Robots with Diffusion Transformers and Bootstrap Training Zhang, Dong Peng, Jingwei Jiao, Yuyang Gu, Jiayuan Yu, Jingyi Chen, Jiahao Robotics This paper presents a novel Expressive Facial Control (ExFace) method based on Diffusion Transformers, which achieves precise mapping from human facial blendshapes to bionic robot motor control. By incorporating an innovative model bootstrap training strategy, our approach not only generates high-quality facial expressions but also significantly improves accuracy and smoothness. Experimental results demonstrate that the proposed method outperforms previous methods in terms of accuracy, frame per second (FPS), and response time. Furthermore, we develop the ExFace dataset driven by human facial data. ExFace shows excellent real-time performance and natural expression rendering in applications such as robot performances and human-robot interactions, offering a new solution for bionic robot interaction. |
| title | ExFace: Expressive Facial Control for Humanoid Robots with Diffusion Transformers and Bootstrap Training |
| topic | Robotics |
| url | https://arxiv.org/abs/2504.14477 |