CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields
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_ | 1866911850518544384 |
|---|---|
| author | Zhang, Deheng Fernandez-Labrador, Clara Schroers, Christopher |
| author_facet | Zhang, Deheng Fernandez-Labrador, Clara Schroers, Christopher |
| contents | Creating artistic 3D scenes can be time-consuming and requires specialized knowledge. To address this, recent works such as ARF, use a radiance field-based approach with style constraints to generate 3D scenes that resemble a style image provided by the user. However, these methods lack fine-grained control over the resulting scenes. In this paper, we introduce Controllable Artistic Radiance Fields (CoARF), a novel algorithm for controllable 3D scene stylization. CoARF enables style transfer for specified objects, compositional 3D style transfer and semantic-aware style transfer. We achieve controllability using segmentation masks with different label-dependent loss functions. We also propose a semantic-aware nearest neighbor matching algorithm to improve the style transfer quality. Our extensive experiments demonstrate that CoARF provides user-specified controllability of style transfer and superior style transfer quality with more precise feature matching. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14967 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields Zhang, Deheng Fernandez-Labrador, Clara Schroers, Christopher Computer Vision and Pattern Recognition Artificial Intelligence Graphics Creating artistic 3D scenes can be time-consuming and requires specialized knowledge. To address this, recent works such as ARF, use a radiance field-based approach with style constraints to generate 3D scenes that resemble a style image provided by the user. However, these methods lack fine-grained control over the resulting scenes. In this paper, we introduce Controllable Artistic Radiance Fields (CoARF), a novel algorithm for controllable 3D scene stylization. CoARF enables style transfer for specified objects, compositional 3D style transfer and semantic-aware style transfer. We achieve controllability using segmentation masks with different label-dependent loss functions. We also propose a semantic-aware nearest neighbor matching algorithm to improve the style transfer quality. Our extensive experiments demonstrate that CoARF provides user-specified controllability of style transfer and superior style transfer quality with more precise feature matching. |
| title | CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2404.14967 |