Dream-in-Style: Text-to-3D Generation Using Stylized Score Distillation
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_ | 1866916611044147200 |
|---|---|
| author | Kompanowski, Hubert Hua, Binh-Son |
| author_facet | Kompanowski, Hubert Hua, Binh-Son |
| contents | We present a method to generate 3D objects in styles. Our method takes a text prompt and a style reference image as input and reconstructs a neural radiance field to synthesize a 3D model with the content aligning with the text prompt and the style following the reference image. To simultaneously generate the 3D object and perform style transfer in one go, we propose a stylized score distillation loss to guide a text-to-3D optimization process to output visually plausible geometry and appearance. Our stylized score distillation is based on a combination of an original pretrained text-to-image model and its modified sibling with the key and value features of self-attention layers manipulated to inject styles from the reference image. Comparisons with state-of-the-art methods demonstrated the strong visual performance of our method, further supported by the quantitative results from our user study. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_18581 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dream-in-Style: Text-to-3D Generation Using Stylized Score Distillation Kompanowski, Hubert Hua, Binh-Son Computer Vision and Pattern Recognition Graphics We present a method to generate 3D objects in styles. Our method takes a text prompt and a style reference image as input and reconstructs a neural radiance field to synthesize a 3D model with the content aligning with the text prompt and the style following the reference image. To simultaneously generate the 3D object and perform style transfer in one go, we propose a stylized score distillation loss to guide a text-to-3D optimization process to output visually plausible geometry and appearance. Our stylized score distillation is based on a combination of an original pretrained text-to-image model and its modified sibling with the key and value features of self-attention layers manipulated to inject styles from the reference image. Comparisons with state-of-the-art methods demonstrated the strong visual performance of our method, further supported by the quantitative results from our user study. |
| title | Dream-in-Style: Text-to-3D Generation Using Stylized Score Distillation |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2406.18581 |