FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908393641345024 |
|---|---|
| author | Liu, Hengyu Wang, Yuehao Li, Chenxin Cai, Ruisi Wang, Kevin Li, Wuyang Molchanov, Pavlo Wang, Peihao Wang, Zhangyang |
| author_facet | Liu, Hengyu Wang, Yuehao Li, Chenxin Cai, Ruisi Wang, Kevin Li, Wuyang Molchanov, Pavlo Wang, Peihao Wang, Zhangyang |
| contents | 3D Gaussian splatting (3DGS) has enabled various applications in 3D scene representation and novel view synthesis due to its efficient rendering capabilities. However, 3DGS demands relatively significant GPU memory, limiting its use on devices with restricted computational resources. Previous approaches have focused on pruning less important Gaussians, effectively compressing 3DGS but often requiring a fine-tuning stage and lacking adaptability for the specific memory needs of different devices. In this work, we present an elastic inference method for 3DGS. Given an input for the desired model size, our method selects and transforms a subset of Gaussians, achieving substantial rendering performance without additional fine-tuning. We introduce a tiny learnable module that controls Gaussian selection based on the input percentage, along with a transformation module that adjusts the selected Gaussians to complement the performance of the reduced model. Comprehensive experiments on ZipNeRF, MipNeRF and Tanks\&Temples scenes demonstrate the effectiveness of our approach. Code is available at https://flexgs.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04174 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting Liu, Hengyu Wang, Yuehao Li, Chenxin Cai, Ruisi Wang, Kevin Li, Wuyang Molchanov, Pavlo Wang, Peihao Wang, Zhangyang Computer Vision and Pattern Recognition 3D Gaussian splatting (3DGS) has enabled various applications in 3D scene representation and novel view synthesis due to its efficient rendering capabilities. However, 3DGS demands relatively significant GPU memory, limiting its use on devices with restricted computational resources. Previous approaches have focused on pruning less important Gaussians, effectively compressing 3DGS but often requiring a fine-tuning stage and lacking adaptability for the specific memory needs of different devices. In this work, we present an elastic inference method for 3DGS. Given an input for the desired model size, our method selects and transforms a subset of Gaussians, achieving substantial rendering performance without additional fine-tuning. We introduce a tiny learnable module that controls Gaussian selection based on the input percentage, along with a transformation module that adjusts the selected Gaussians to complement the performance of the reduced model. Comprehensive experiments on ZipNeRF, MipNeRF and Tanks\&Temples scenes demonstrate the effectiveness of our approach. Code is available at https://flexgs.github.io. |
| title | FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.04174 |