3D Gaussian splatting has achieved very impressive performance in real-time novel view synthesis. However, it often suffers from over-reconstruction during Gaussian densification where high-variance image regions are covered by a few large Gaussians only, leading to blur and artifacts in the rendered images. We design a progressive frequency regularization (FreGS) technique to tackle the over-reconstruction issue within the frequency space. Specifically, FreGS performs coarse-to-fine Gaussian densification by exploiting low-to-high frequency components that can be easily extracted with low-pass and high-pass filters in the Fourier space. By minimizing the discrepancy between the frequency spectrum of the rendered image and the corresponding ground truth, it achieves high-quality Gaussian densification and alleviates the over-reconstruction of Gaussian splatting effectively. Experiments over multiple widely adopted benchmarks (e.g., Mip-NeRF360, Tanks-and-Temples and Deep Blending) show that FreGS achieves superior novel view synthesis and outperforms the state-of-the-art consistently.

翻译：摘要：三维高斯溅射在实时新视角合成中取得了非常显著的性能。然而，在高斯稠密化过程中，当高方差图像区域仅被少数几个大高斯覆盖时，该方法常出现过度重建问题，导致渲染图像出现模糊和伪影。我们提出了一种渐进频率正则化（FreGS）技术，以在频率空间中解决过度重建问题。具体而言，FreGS利用傅里叶空间中可通过低通和高通滤波器轻松提取的低频到高频分量，执行从粗到细的高斯稠密化。通过最小化渲染图像频谱与对应真实值之间的差异，该方法实现了高质量的高斯稠密化，并有效缓解了高斯溅射的过度重建问题。在多个广泛采用的基准（如Mip-NeRF360、Tanks-and-Temples和Deep Blending）上的实验表明，FreGS在新视角合成中表现卓越，持续优于现有最先进方法。