Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912074857185280 |
|---|---|
| author | Ren, Kerui Jiang, Lihan Lu, Tao Yu, Mulin Xu, Linning Ni, Zhangkai Dai, Bo |
| author_facet | Ren, Kerui Jiang, Lihan Lu, Tao Yu, Mulin Xu, Linning Ni, Zhangkai Dai, Bo |
| contents | The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and efficiency compared to NeRF-based neural scene representations. While demonstrating the potential for real-time rendering, 3D-GS encounters rendering bottlenecks in large scenes with complex details due to an excessive number of Gaussian primitives located within the viewing frustum. This limitation is particularly noticeable in zoom-out views and can lead to inconsistent rendering speeds in scenes with varying details. Moreover, it often struggles to capture the corresponding level of details at different scales with its heuristic density control operation. Inspired by the Level-of-Detail (LOD) techniques, we introduce Octree-GS, featuring an LOD-structured 3D Gaussian approach supporting level-of-detail decomposition for scene representation that contributes to the final rendering results. Our model dynamically selects the appropriate level from the set of multi-resolution anchor points, ensuring consistent rendering performance with adaptive LOD adjustments while maintaining high-fidelity rendering results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17898 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians Ren, Kerui Jiang, Lihan Lu, Tao Yu, Mulin Xu, Linning Ni, Zhangkai Dai, Bo Computer Vision and Pattern Recognition The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and efficiency compared to NeRF-based neural scene representations. While demonstrating the potential for real-time rendering, 3D-GS encounters rendering bottlenecks in large scenes with complex details due to an excessive number of Gaussian primitives located within the viewing frustum. This limitation is particularly noticeable in zoom-out views and can lead to inconsistent rendering speeds in scenes with varying details. Moreover, it often struggles to capture the corresponding level of details at different scales with its heuristic density control operation. Inspired by the Level-of-Detail (LOD) techniques, we introduce Octree-GS, featuring an LOD-structured 3D Gaussian approach supporting level-of-detail decomposition for scene representation that contributes to the final rendering results. Our model dynamically selects the appropriate level from the set of multi-resolution anchor points, ensuring consistent rendering performance with adaptive LOD adjustments while maintaining high-fidelity rendering results. |
| title | Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.17898 |