Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908492811468800 |
|---|---|
| author | Aloni, Yaron Shalev-Arkushin, Rotem Shafir, Yonatan Tevet, Guy Fried, Ohad Bermano, Amit Haim |
| author_facet | Aloni, Yaron Shalev-Arkushin, Rotem Shafir, Yonatan Tevet, Guy Fried, Ohad Bermano, Amit Haim |
| contents | Dynamic facial expression generation from natural language is a crucial task in Computer Graphics, with applications in Animation, Virtual Avatars, and Human-Computer Interaction. However, current generative models suffer from datasets that are either speech-driven or limited to coarse emotion labels, lacking the nuanced, expressive descriptions needed for fine-grained control, and were captured using elaborate and expensive equipment. We hence present a new dataset of facial motion sequences featuring nuanced performances and semantic annotation. The data is easily collected using commodity equipment and LLM-generated natural language instructions, in the popular ARKit blendshape format. This provides riggable motion, rich with expressive performances and labels. We accordingly train two baseline models, and evaluate their performance for future benchmarking. Using our Express4D dataset, the trained models can learn meaningful text-to-expression motion generation and capture the many-to-many mapping of the two modalities. The dataset, code, and video examples are available on our webpage: https://jaron1990.github.io/Express4D/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12438 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark Aloni, Yaron Shalev-Arkushin, Rotem Shafir, Yonatan Tevet, Guy Fried, Ohad Bermano, Amit Haim Graphics Computer Vision and Pattern Recognition Dynamic facial expression generation from natural language is a crucial task in Computer Graphics, with applications in Animation, Virtual Avatars, and Human-Computer Interaction. However, current generative models suffer from datasets that are either speech-driven or limited to coarse emotion labels, lacking the nuanced, expressive descriptions needed for fine-grained control, and were captured using elaborate and expensive equipment. We hence present a new dataset of facial motion sequences featuring nuanced performances and semantic annotation. The data is easily collected using commodity equipment and LLM-generated natural language instructions, in the popular ARKit blendshape format. This provides riggable motion, rich with expressive performances and labels. We accordingly train two baseline models, and evaluate their performance for future benchmarking. Using our Express4D dataset, the trained models can learn meaningful text-to-expression motion generation and capture the many-to-many mapping of the two modalities. The dataset, code, and video examples are available on our webpage: https://jaron1990.github.io/Express4D/ |
| title | Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.12438 |