Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation
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_ | 1866911422023204864 |
|---|---|
| author | Cai, Yunxuan Xiang, Sitao Li, Zongjian Chen, Haiwei Zhao, Yajie |
| author_facet | Cai, Yunxuan Xiang, Sitao Li, Zongjian Chen, Haiwei Zhao, Yajie |
| contents | Digital modeling and reconstruction of human faces serve various applications. However, its availability is often hindered by the requirements of data capturing devices, manual labor, and suitable actors. This situation restricts the diversity, expressiveness, and control over the resulting models. This work aims to demonstrate that a semantically controllable generative network can provide enhanced control over the digital face modeling process. To enhance diversity beyond the limited human faces scanned in a controlled setting, we introduce a novel data generation pipeline that creates a high-quality 3D face database using a pre-trained diffusion model. Our proposed normalization module converts synthesized data from the diffusion model into high-quality scanned data. Using the 44,000 face models we obtained, we further developed an efficient GAN-based generator. This generator accepts semantic attributes as input, and generates geometry and albedo. It also allows continuous post-editing of attributes in the latent space. Our asset refinement component subsequently creates physically-based facial assets. We introduce a comprehensive system designed for creating and editing high-quality face assets. Our proposed model has undergone extensive experiment, comparison and evaluation. We also integrate everything into a web-based interactive tool. We aim to make this tool publicly available with the release of the paper. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15259 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation Cai, Yunxuan Xiang, Sitao Li, Zongjian Chen, Haiwei Zhao, Yajie Computer Vision and Pattern Recognition Artificial Intelligence Digital modeling and reconstruction of human faces serve various applications. However, its availability is often hindered by the requirements of data capturing devices, manual labor, and suitable actors. This situation restricts the diversity, expressiveness, and control over the resulting models. This work aims to demonstrate that a semantically controllable generative network can provide enhanced control over the digital face modeling process. To enhance diversity beyond the limited human faces scanned in a controlled setting, we introduce a novel data generation pipeline that creates a high-quality 3D face database using a pre-trained diffusion model. Our proposed normalization module converts synthesized data from the diffusion model into high-quality scanned data. Using the 44,000 face models we obtained, we further developed an efficient GAN-based generator. This generator accepts semantic attributes as input, and generates geometry and albedo. It also allows continuous post-editing of attributes in the latent space. Our asset refinement component subsequently creates physically-based facial assets. We introduce a comprehensive system designed for creating and editing high-quality face assets. Our proposed model has undergone extensive experiment, comparison and evaluation. We also integrate everything into a web-based interactive tool. We aim to make this tool publicly available with the release of the paper. |
| title | Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.15259 |