Gaussian splatting methods are emerging as a popular approach for converting multi-view image data into scene representations that allow view synthesis. In particular, there is interest in enabling view synthesis for dynamic scenes using only monocular input data -- an ill-posed and challenging problem. The fast pace of work in this area has produced multiple simultaneous papers that claim to work best, which cannot all be true. In this work, we organize, benchmark, and analyze many Gaussian-splatting-based methods, providing apples-to-apples comparisons that prior works have lacked. We use multiple existing datasets and a new instructive synthetic dataset designed to isolate factors that affect reconstruction quality. We systematically categorize Gaussian splatting methods into specific motion representation types and quantify how their differences impact performance. Empirically, we find that their rank order is well-defined in synthetic data, but the complexity of real-world data currently overwhelms the differences. Furthermore, the fast rendering speed of all Gaussian-based methods comes at the cost of brittleness in optimization. We summarize our experiments into a list of findings that can help to further progress in this lively problem setting.
高斯点绘方法正在成为一种流行的技术，用于将多视角图像数据转换为可实现视图合成的场景表示。尤其是在仅使用单目输入数据的情况下实现动态场景的视图合成，这一问题因其病态性和挑战性而备受关注。近期，该领域的快速发展带来了多个几乎同时发表的论文，每篇都声称其方法是最优的，但这些说法显然不可能全部成立。 在本文中，我们对许多基于高斯点绘的方法进行了组织、基准测试和分析，提供了前人研究中缺乏的“等量齐观”比较。我们使用多个现有数据集，以及一个新设计的教学性合成数据集，该数据集旨在分离影响重建质量的关键因素。我们系统地将高斯点绘方法按运动表示类型进行分类，并量化它们在性能上的差异。 实验结果表明，在合成数据中，这些方法的优劣顺序非常清晰，但在真实世界的数据中，数据复杂性会掩盖这些差异。此外，尽管所有基于高斯的方法在渲染速度上具有显著优势，但这种速度以优化过程的脆弱性为代价。 我们将实验总结为一系列发现，为这一活跃的研究领域提供了指导，旨在推动进一步的进展。