FlexiTex: Enhancing Texture Generation via Visual Guidance
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912491479498752 |
|---|---|
| author | Jiang, DaDong Yang, Xianghui Zhao, Zibo Zhang, Sheng Yu, Jiaao Lai, Zeqiang Yang, Shaoxiong Guo, Chunchao Zhou, Xiaobo Ke, Zhihui |
| author_facet | Jiang, DaDong Yang, Xianghui Zhao, Zibo Zhang, Sheng Yu, Jiaao Lai, Zeqiang Yang, Shaoxiong Guo, Chunchao Zhou, Xiaobo Ke, Zhihui |
| contents | Recent texture generation methods achieve impressive results due to the powerful generative prior they leverage from large-scale text-to-image diffusion models. However, abstract textual prompts are limited in providing global textural or shape information, which results in the texture generation methods producing blurry or inconsistent patterns. To tackle this, we present FlexiTex, embedding rich information via visual guidance to generate a high-quality texture. The core of FlexiTex is the Visual Guidance Enhancement module, which incorporates more specific information from visual guidance to reduce ambiguity in the text prompt and preserve high-frequency details. To further enhance the visual guidance, we introduce a Direction-Aware Adaptation module that automatically designs direction prompts based on different camera poses, avoiding the Janus problem and maintaining semantically global consistency. Benefiting from the visual guidance, FlexiTex produces quantitatively and qualitatively sound results, demonstrating its potential to advance texture generation for real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12431 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FlexiTex: Enhancing Texture Generation via Visual Guidance Jiang, DaDong Yang, Xianghui Zhao, Zibo Zhang, Sheng Yu, Jiaao Lai, Zeqiang Yang, Shaoxiong Guo, Chunchao Zhou, Xiaobo Ke, Zhihui Computer Vision and Pattern Recognition Artificial Intelligence Recent texture generation methods achieve impressive results due to the powerful generative prior they leverage from large-scale text-to-image diffusion models. However, abstract textual prompts are limited in providing global textural or shape information, which results in the texture generation methods producing blurry or inconsistent patterns. To tackle this, we present FlexiTex, embedding rich information via visual guidance to generate a high-quality texture. The core of FlexiTex is the Visual Guidance Enhancement module, which incorporates more specific information from visual guidance to reduce ambiguity in the text prompt and preserve high-frequency details. To further enhance the visual guidance, we introduce a Direction-Aware Adaptation module that automatically designs direction prompts based on different camera poses, avoiding the Janus problem and maintaining semantically global consistency. Benefiting from the visual guidance, FlexiTex produces quantitatively and qualitatively sound results, demonstrating its potential to advance texture generation for real-world applications. |
| title | FlexiTex: Enhancing Texture Generation via Visual Guidance |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2409.12431 |