Recent approaches representing 3D objects and scenes using Gaussian splats show increased rendering speed across a variety of platforms and devices. While rendering such representations is indeed extremely efficient, storing and transmitting them is often prohibitively expensive. To represent large-scale scenes, one often needs to store millions of 3D Gaussians, occupying gigabytes of disk space. This poses a very practical limitation, prohibiting widespread adoption.Several solutions have been proposed to strike a balance between disk size and rendering quality, noticeably reducing the visual quality. In this work, we propose a new representation that dramatically reduces the hard drive footprint while featuring similar or improved quality when compared to the standard 3D Gaussian splats. When compared to other compact solutions, ours offers higher quality renderings with significantly reduced storage, being able to efficiently run on a mobile device in real-time. Our key observation is that nearby points in the scene can share similar representations. Hence, only a small ratio of 3D points needs to be stored. We introduce an approach to identify such points which are called parent points. The discarded points called children points along with attributes can be efficiently predicted by tiny MLPs.

翻译：近期采用高斯溅射表示三维物体与场景的方法，在各种平台与设备上均展现出渲染速度的提升。尽管此类表示的渲染效率极高，但其存储与传输成本往往过于高昂。为表示大规模场景，通常需要存储数百万个三维高斯函数，占用数十GB的磁盘空间。这构成了实际应用中的显著限制，阻碍了该技术的广泛采用。现有解决方案尝试在存储规模与渲染质量间寻求平衡，但往往以显著降低视觉质量为代价。本研究提出一种新型表示方法，在保持或提升标准三维高斯溅射质量的同时，大幅降低硬盘存储需求。相较于其他紧凑型方案，本方法能以显著减少的存储空间实现更高质量的渲染，并能在移动设备上实时高效运行。我们的核心发现是：场景中相邻空间点可共享相似的表征形式。因此，仅需存储小比例的三维空间点。我们提出一种识别此类"父节点"的方法，而被称为"子节点"的剔除点及其属性可通过微型MLP进行高效预测。