arXiv 2510.078302025-10-09cs.CV

PrismGS：面向高保真大规模3D高斯泼溅的物理基础抗锯齿方法

PrismGS: Physically-Grounded Anti-Aliasing for High-Fidelity Large-Scale 3D Gaussian Splatting

School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China（上海交通大学信息科学与电子工程学院）；Cooperative Mediant Innovation Center, Shanghai Jiao Tong University, Shanghai, China（上海交通大学协同创新中心）；College of Information Science and Technology, Eastern Institute of Technology, Ningbo, China（宁波工程技术学院信息科学与技术学院）

Houqiang Zhong, Zhenglong Wu, Sihua Fu, Zihan Zheng, Xin Jin, Xiaoyun Zhang, Li Song, Qiang Hu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

PrismGS提出物理基础正则化框架，通过金字塔多尺度监督和尺寸下界约束，解决大规模3DGS在高分辨率下的锯齿与闪烁问题，实现即插即用，在多个城市数据集上较CityGaussian提升约1.5 dB PSNR。

摘要：

3D高斯泼溅（3DGS）近期在紧凑场景中实现了实时照片级逼真渲染，但扩展到大型城市场景时引入了严重的锯齿伪影和优化不稳定性，尤其是在高分辨率（如4K）渲染下。这些伪影表现为闪烁纹理和锯齿边缘，源于高斯基元与城市几何多尺度特性之间的不匹配。虽然现有的“分而治之”流程解决了可扩展性问题，但未能解决这一保真度差距。本文提出PrismGS，一种物理基础的正则化框架，旨在改善3D高斯的内在渲染行为。PrismGS整合了两个协同正则化器。第一个是金字塔多尺度监督，通过对预滤波图像金字塔的渲染进行监督来强制一致性，迫使模型学习一种内在抗锯齿的表示，在不同观看尺度下保持一致，直接缓解闪烁纹理。第二个是显式尺寸正则化，对3D高斯的尺寸施加物理基础的下界，防止形成退化的、视图依赖的基元，从而产生更稳定和合理的几何表面，减少锯齿边缘。我们的方法是即插即用的，与现有流程兼容。在MatrixCity、Mill-19和UrbanScene3D上的大量实验表明，PrismGS达到了最先进的性能，相比CityGaussian获得了约1.5 dB的显著PSNR提升，同时在苛刻的4K渲染下保持了其卓越的质量和鲁棒性。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。