Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.07830 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918157158973440 |
|---|---|
| author | Zhong, Houqiang Wu, Zhenglong Fu, Sihua Zheng, Zihan Jin, Xin Zhang, Xiaoyun Song, Li Hu, Qiang |
| author_facet | Zhong, Houqiang Wu, Zhenglong Fu, Sihua Zheng, Zihan Jin, Xin Zhang, Xiaoyun Song, Li Hu, Qiang |
| contents | 3D Gaussian Splatting (3DGS) has recently enabled real-time photorealistic rendering in compact scenes, but scaling to large urban environments introduces severe aliasing artifacts and optimization instability, especially under high-resolution (e.g., 4K) rendering. These artifacts, manifesting as flickering textures and jagged edges, arise from the mismatch between Gaussian primitives and the multi-scale nature of urban geometry. While existing ``divide-and-conquer'' pipelines address scalability, they fail to resolve this fidelity gap. In this paper, we propose PrismGS, a physically-grounded regularization framework that improves the intrinsic rendering behavior of 3D Gaussians. PrismGS integrates two synergistic regularizers. The first is pyramidal multi-scale supervision, which enforces consistency by supervising the rendering against a pre-filtered image pyramid. This compels the model to learn an inherently anti-aliased representation that remains coherent across different viewing scales, directly mitigating flickering textures. This is complemented by an explicit size regularization that imposes a physically-grounded lower bound on the dimensions of the 3D Gaussians. This prevents the formation of degenerate, view-dependent primitives, leading to more stable and plausible geometric surfaces and reducing jagged edges. Our method is plug-and-play and compatible with existing pipelines. Extensive experiments on MatrixCity, Mill-19, and UrbanScene3D demonstrate that PrismGS achieves state-of-the-art performance, yielding significant PSNR gains around 1.5 dB against CityGaussian, while maintaining its superior quality and robustness under demanding 4K rendering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07830 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PrismGS: Physically-Grounded Anti-Aliasing for High-Fidelity Large-Scale 3D Gaussian Splatting Zhong, Houqiang Wu, Zhenglong Fu, Sihua Zheng, Zihan Jin, Xin Zhang, Xiaoyun Song, Li Hu, Qiang Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) has recently enabled real-time photorealistic rendering in compact scenes, but scaling to large urban environments introduces severe aliasing artifacts and optimization instability, especially under high-resolution (e.g., 4K) rendering. These artifacts, manifesting as flickering textures and jagged edges, arise from the mismatch between Gaussian primitives and the multi-scale nature of urban geometry. While existing ``divide-and-conquer'' pipelines address scalability, they fail to resolve this fidelity gap. In this paper, we propose PrismGS, a physically-grounded regularization framework that improves the intrinsic rendering behavior of 3D Gaussians. PrismGS integrates two synergistic regularizers. The first is pyramidal multi-scale supervision, which enforces consistency by supervising the rendering against a pre-filtered image pyramid. This compels the model to learn an inherently anti-aliased representation that remains coherent across different viewing scales, directly mitigating flickering textures. This is complemented by an explicit size regularization that imposes a physically-grounded lower bound on the dimensions of the 3D Gaussians. This prevents the formation of degenerate, view-dependent primitives, leading to more stable and plausible geometric surfaces and reducing jagged edges. Our method is plug-and-play and compatible with existing pipelines. Extensive experiments on MatrixCity, Mill-19, and UrbanScene3D demonstrate that PrismGS achieves state-of-the-art performance, yielding significant PSNR gains around 1.5 dB against CityGaussian, while maintaining its superior quality and robustness under demanding 4K rendering. |
| title | PrismGS: Physically-Grounded Anti-Aliasing for High-Fidelity Large-Scale 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.07830 |