Isotropic Gaussian Splatting for Real-Time Radiance Field Rendering
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_ | 1866913276429860864 |
|---|---|
| author | Gong, Yuanhao Yu, Lantao Yue, Guanghui |
| author_facet | Gong, Yuanhao Yu, Lantao Yue, Guanghui |
| contents | The 3D Gaussian splatting method has drawn a lot of attention, thanks to its high performance in training and high quality of the rendered image. However, it uses anisotropic Gaussian kernels to represent the scene. Although such anisotropic kernels have advantages in representing the geometry, they lead to difficulties in terms of computation, such as splitting or merging two kernels. In this paper, we propose to use isotropic Gaussian kernels to avoid such difficulties in the computation, leading to a higher performance method. The experiments confirm that the proposed method is about {\bf 100X} faster without losing the geometry representation accuracy. The proposed method can be applied in a large range applications where the radiance field is needed, such as 3D reconstruction, view synthesis, and dynamic object modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14244 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Isotropic Gaussian Splatting for Real-Time Radiance Field Rendering Gong, Yuanhao Yu, Lantao Yue, Guanghui Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing The 3D Gaussian splatting method has drawn a lot of attention, thanks to its high performance in training and high quality of the rendered image. However, it uses anisotropic Gaussian kernels to represent the scene. Although such anisotropic kernels have advantages in representing the geometry, they lead to difficulties in terms of computation, such as splitting or merging two kernels. In this paper, we propose to use isotropic Gaussian kernels to avoid such difficulties in the computation, leading to a higher performance method. The experiments confirm that the proposed method is about {\bf 100X} faster without losing the geometry representation accuracy. The proposed method can be applied in a large range applications where the radiance field is needed, such as 3D reconstruction, view synthesis, and dynamic object modeling. |
| title | Isotropic Gaussian Splatting for Real-Time Radiance Field Rendering |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2403.14244 |