3D Gaussian Splatting (3DGS) has emerged as a mainstream for novel view synthesis, leveraging continuous aggregations of Gaussian functions to model scene geometry. However, 3DGS suffers from substantial memory requirements to store the multitude of Gaussians, hindering its practicality. To address this challenge, we introduce GaussianSpa, an optimization-based simplification framework for compact and high-quality 3DGS. Specifically, we formulate the simplification as an optimization problem associated with the 3DGS training. Correspondingly, we propose an efficient "optimizing-sparsifying" solution that alternately solves two independent sub-problems, gradually imposing strong sparsity onto the Gaussians in the training process. Our comprehensive evaluations on various datasets show the superiority of GaussianSpa over existing state-of-the-art approaches. Notably, GaussianSpa achieves an average PSNR improvement of 0.9 dB on the real-world Deep Blending dataset with 10$\times$ fewer Gaussians compared to the vanilla 3DGS. Our project page is available at https://gaussianspa.github.io/.

翻译：三维高斯溅射（3DGS）已成为新视角合成的主流方法，其利用高斯函数的连续聚合来建模场景几何。然而，3DGS需要大量内存来存储众多高斯函数，限制了其实用性。为解决这一问题，我们提出了GaussianSpa——一种基于优化的简化框架，旨在实现紧凑且高质量的3DGS。具体而言，我们将简化过程构建为与3DGS训练相关的优化问题，并相应提出了一种高效的“优化-稀疏化”解决方案。该方法通过交替求解两个独立子问题，在训练过程中逐步对高斯函数施加强稀疏性约束。我们在多个数据集上的综合评估表明，GaussianSpa优于现有最先进方法。值得注意的是，在真实世界Deep Blending数据集上，GaussianSpa仅使用原始3DGS十分之一的高斯函数数量，即实现了平均PSNR指标0.9 dB的提升。项目页面详见 https://gaussianspa.github.io/。