FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929462766993408 |
|---|---|
| author | Feng, Guofeng Chen, Siyan Fu, Rong Liao, Zimu Wang, Yi Liu, Tao Pei, Zhilin Li, Hengjie Zhang, Xingcheng Dai, Bo |
| author_facet | Feng, Guofeng Chen, Siyan Fu, Rong Liao, Zimu Wang, Yi Liu, Tao Pei, Zhilin Li, Hengjie Zhang, Xingcheng Dai, Bo |
| contents | This work introduces FlashGS, an open-source CUDA Python library, designed to facilitate the efficient differentiable rasterization of 3D Gaussian Splatting through algorithmic and kernel-level optimizations. FlashGS is developed based on the observations from a comprehensive analysis of the rendering process to enhance computational efficiency and bring the technique to wide adoption. The paper includes a suite of optimization strategies, encompassing redundancy elimination, efficient pipelining, refined control and scheduling mechanisms, and memory access optimizations, all of which are meticulously integrated to amplify the performance of the rasterization process. An extensive evaluation of FlashGS' performance has been conducted across a diverse spectrum of synthetic and real-world large-scale scenes, encompassing a variety of image resolutions. The empirical findings demonstrate that FlashGS consistently achieves an average 4x acceleration over mobile consumer GPUs, coupled with reduced memory consumption. These results underscore the superior performance and resource optimization capabilities of FlashGS, positioning it as a formidable tool in the domain of 3D rendering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07967 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering Feng, Guofeng Chen, Siyan Fu, Rong Liao, Zimu Wang, Yi Liu, Tao Pei, Zhilin Li, Hengjie Zhang, Xingcheng Dai, Bo Computer Vision and Pattern Recognition This work introduces FlashGS, an open-source CUDA Python library, designed to facilitate the efficient differentiable rasterization of 3D Gaussian Splatting through algorithmic and kernel-level optimizations. FlashGS is developed based on the observations from a comprehensive analysis of the rendering process to enhance computational efficiency and bring the technique to wide adoption. The paper includes a suite of optimization strategies, encompassing redundancy elimination, efficient pipelining, refined control and scheduling mechanisms, and memory access optimizations, all of which are meticulously integrated to amplify the performance of the rasterization process. An extensive evaluation of FlashGS' performance has been conducted across a diverse spectrum of synthetic and real-world large-scale scenes, encompassing a variety of image resolutions. The empirical findings demonstrate that FlashGS consistently achieves an average 4x acceleration over mobile consumer GPUs, coupled with reduced memory consumption. These results underscore the superior performance and resource optimization capabilities of FlashGS, positioning it as a formidable tool in the domain of 3D rendering. |
| title | FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.07967 |