Geometry Transfer for Stylizing 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_ | 1866914743176921088 |
|---|---|
| author | Jung, Hyunyoung Nam, Seonghyeon Sarafianos, Nikolaos Yoo, Sungjoo Sorkine-Hornung, Alexander Ranjan, Rakesh |
| author_facet | Jung, Hyunyoung Nam, Seonghyeon Sarafianos, Nikolaos Yoo, Sungjoo Sorkine-Hornung, Alexander Ranjan, Rakesh |
| contents | Shape and geometric patterns are essential in defining stylistic identity. However, current 3D style transfer methods predominantly focus on transferring colors and textures, often overlooking geometric aspects. In this paper, we introduce Geometry Transfer, a novel method that leverages geometric deformation for 3D style transfer. This technique employs depth maps to extract a style guide, subsequently applied to stylize the geometry of radiance fields. Moreover, we propose new techniques that utilize geometric cues from the 3D scene, thereby enhancing aesthetic expressiveness and more accurately reflecting intended styles. Our extensive experiments show that Geometry Transfer enables a broader and more expressive range of stylizations, thereby significantly expanding the scope of 3D style transfer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_00863 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Geometry Transfer for Stylizing Radiance Fields Jung, Hyunyoung Nam, Seonghyeon Sarafianos, Nikolaos Yoo, Sungjoo Sorkine-Hornung, Alexander Ranjan, Rakesh Computer Vision and Pattern Recognition Shape and geometric patterns are essential in defining stylistic identity. However, current 3D style transfer methods predominantly focus on transferring colors and textures, often overlooking geometric aspects. In this paper, we introduce Geometry Transfer, a novel method that leverages geometric deformation for 3D style transfer. This technique employs depth maps to extract a style guide, subsequently applied to stylize the geometry of radiance fields. Moreover, we propose new techniques that utilize geometric cues from the 3D scene, thereby enhancing aesthetic expressiveness and more accurately reflecting intended styles. Our extensive experiments show that Geometry Transfer enables a broader and more expressive range of stylizations, thereby significantly expanding the scope of 3D style transfer. |
| title | Geometry Transfer for Stylizing Radiance Fields |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.00863 |