MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914536162852864 |
|---|---|
| author | Xie, Shuzhao Ge, Junchen Zhang, Weixiang Liu, Jiahang Tang, Chen Bai, Yunpeng Ge, Shijia Jiang, Jingyan Huang, Yuzhi Yang, Fengnian Zhang, Cong Fan, Xiaoyi Wang, Zhi |
| author_facet | Xie, Shuzhao Ge, Junchen Zhang, Weixiang Liu, Jiahang Tang, Chen Bai, Yunpeng Ge, Shijia Jiang, Jingyan Huang, Yuzhi Yang, Fengnian Zhang, Cong Fan, Xiaoyi Wang, Zhi |
| contents | 3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-training compression methods still rely on many coupled hyperparameters across pruning, transformation, quantization, and entropy coding, making it difficult to control the final compressed size and fully exploit the rate-distortion trade-off. We propose MesonGS++, a size-aware post-training codec for 3D Gaussian compression. On the codec side, MesonGS++ combines joint importance-based pruning, octree geometry coding, attribute transformation, selective vector quantization for higher-degree spherical harmonics, and group-wise mixed-precision quantization with entropy coding. On the configuration side, it treats the reserve ratio and bit-width allocation as the dominant rate-distortion knobs and jointly optimizes them under a target storage budget via discrete sampling and 0--1 integer linear programming. We further propose a linear size estimator and a CUDA parallel quantization operator to accelerate the hyperparameter searching process. Extensive experiments show that MesonGS++ achieves over 34$\times$ compression while preserving rendering fidelity, outperforming state-of-the-art post-training methods and accurately meeting target size budgets. Remarkably, without any training, MesonGS++ can even surpass the PSNR of vanilla 3DGS at a 20$\times$ compression rate on the Stump scene. Our code is available at https://github.com/mmlab-sigs/mesongs_plus |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26799 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching Xie, Shuzhao Ge, Junchen Zhang, Weixiang Liu, Jiahang Tang, Chen Bai, Yunpeng Ge, Shijia Jiang, Jingyan Huang, Yuzhi Yang, Fengnian Zhang, Cong Fan, Xiaoyi Wang, Zhi Computer Vision and Pattern Recognition Graphics Multimedia 3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-training compression methods still rely on many coupled hyperparameters across pruning, transformation, quantization, and entropy coding, making it difficult to control the final compressed size and fully exploit the rate-distortion trade-off. We propose MesonGS++, a size-aware post-training codec for 3D Gaussian compression. On the codec side, MesonGS++ combines joint importance-based pruning, octree geometry coding, attribute transformation, selective vector quantization for higher-degree spherical harmonics, and group-wise mixed-precision quantization with entropy coding. On the configuration side, it treats the reserve ratio and bit-width allocation as the dominant rate-distortion knobs and jointly optimizes them under a target storage budget via discrete sampling and 0--1 integer linear programming. We further propose a linear size estimator and a CUDA parallel quantization operator to accelerate the hyperparameter searching process. Extensive experiments show that MesonGS++ achieves over 34$\times$ compression while preserving rendering fidelity, outperforming state-of-the-art post-training methods and accurately meeting target size budgets. Remarkably, without any training, MesonGS++ can even surpass the PSNR of vanilla 3DGS at a 20$\times$ compression rate on the Stump scene. Our code is available at https://github.com/mmlab-sigs/mesongs_plus |
| title | MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching |
| topic | Computer Vision and Pattern Recognition Graphics Multimedia |
| url | https://arxiv.org/abs/2604.26799 |