Text-Driven Diverse Facial Texture Generation via Progressive Latent-Space Refinement
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909169826660352 |
|---|---|
| author | Wang, Chi Huang, Junming Zhang, Rong Wang, Qi Yang, Haotian Huang, Haibin Ma, Chongyang Xu, Weiwei |
| author_facet | Wang, Chi Huang, Junming Zhang, Rong Wang, Qi Yang, Haotian Huang, Haibin Ma, Chongyang Xu, Weiwei |
| contents | Automatic 3D facial texture generation has gained significant interest recently. Existing approaches may not support the traditional physically based rendering pipeline or rely on 3D data captured by Light Stage. Our key contribution is a progressive latent space refinement approach that can bootstrap from 3D Morphable Models (3DMMs)-based texture maps generated from facial images to generate high-quality and diverse PBR textures, including albedo, normal, and roughness. It starts with enhancing Generative Adversarial Networks (GANs) for text-guided and diverse texture generation. To this end, we design a self-supervised paradigm to overcome the reliance on ground truth 3D textures and train the generative model with only entangled texture maps. Besides, we foster mutual enhancement between GANs and Score Distillation Sampling (SDS). SDS boosts GANs with more generative modes, while GANs promote more efficient optimization of SDS. Furthermore, we introduce an edge-aware SDS for multi-view consistent facial structure. Experiments demonstrate that our method outperforms existing 3D texture generation methods regarding photo-realistic quality, diversity, and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09540 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Text-Driven Diverse Facial Texture Generation via Progressive Latent-Space Refinement Wang, Chi Huang, Junming Zhang, Rong Wang, Qi Yang, Haotian Huang, Haibin Ma, Chongyang Xu, Weiwei Computer Vision and Pattern Recognition Automatic 3D facial texture generation has gained significant interest recently. Existing approaches may not support the traditional physically based rendering pipeline or rely on 3D data captured by Light Stage. Our key contribution is a progressive latent space refinement approach that can bootstrap from 3D Morphable Models (3DMMs)-based texture maps generated from facial images to generate high-quality and diverse PBR textures, including albedo, normal, and roughness. It starts with enhancing Generative Adversarial Networks (GANs) for text-guided and diverse texture generation. To this end, we design a self-supervised paradigm to overcome the reliance on ground truth 3D textures and train the generative model with only entangled texture maps. Besides, we foster mutual enhancement between GANs and Score Distillation Sampling (SDS). SDS boosts GANs with more generative modes, while GANs promote more efficient optimization of SDS. Furthermore, we introduce an edge-aware SDS for multi-view consistent facial structure. Experiments demonstrate that our method outperforms existing 3D texture generation methods regarding photo-realistic quality, diversity, and efficiency. |
| title | Text-Driven Diverse Facial Texture Generation via Progressive Latent-Space Refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.09540 |