Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910900474085376 |
|---|---|
| author | Mi, Yuxi Zhong, Zhizhou Huang, Yuge Yuan, Qiuyang Zhao, Xuan Xu, Jianqing Ding, Shouhong Wang, ShaoMing Guo, Rizen Zhou, Shuigeng |
| author_facet | Mi, Yuxi Zhong, Zhizhou Huang, Yuge Yuan, Qiuyang Zhao, Xuan Xu, Jianqing Ding, Shouhong Wang, ShaoMing Guo, Rizen Zhou, Shuigeng |
| contents | Identity-preserving face synthesis aims to generate synthetic face images of virtual subjects that can substitute real-world data for training face recognition models. While prior arts strive to create images with consistent identities and diverse styles, they face a trade-off between them. Identifying their limitation of treating style variation as subject-agnostic and observing that real-world persons actually have distinct, subject-specific styles, this paper introduces MorphFace, a diffusion-based face generator. The generator learns fine-grained facial styles, e.g., shape, pose and expression, from the renderings of a 3D morphable model (3DMM). It also learns identities from an off-the-shelf recognition model. To create virtual faces, the generator is conditioned on novel identities of unlabeled synthetic faces, and novel styles that are statistically sampled from a real-world prior distribution. The sampling especially accounts for both intra-subject variation and subject distinctiveness. A context blending strategy is employed to enhance the generator's responsiveness to identity and style conditions. Extensive experiments show that MorphFace outperforms the best prior arts in face recognition efficacy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00430 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion Mi, Yuxi Zhong, Zhizhou Huang, Yuge Yuan, Qiuyang Zhao, Xuan Xu, Jianqing Ding, Shouhong Wang, ShaoMing Guo, Rizen Zhou, Shuigeng Computer Vision and Pattern Recognition Identity-preserving face synthesis aims to generate synthetic face images of virtual subjects that can substitute real-world data for training face recognition models. While prior arts strive to create images with consistent identities and diverse styles, they face a trade-off between them. Identifying their limitation of treating style variation as subject-agnostic and observing that real-world persons actually have distinct, subject-specific styles, this paper introduces MorphFace, a diffusion-based face generator. The generator learns fine-grained facial styles, e.g., shape, pose and expression, from the renderings of a 3D morphable model (3DMM). It also learns identities from an off-the-shelf recognition model. To create virtual faces, the generator is conditioned on novel identities of unlabeled synthetic faces, and novel styles that are statistically sampled from a real-world prior distribution. The sampling especially accounts for both intra-subject variation and subject distinctiveness. A context blending strategy is employed to enhance the generator's responsiveness to identity and style conditions. Extensive experiments show that MorphFace outperforms the best prior arts in face recognition efficacy. |
| title | Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.00430 |