Rendering novel view images in dynamic scenes is a crucial yet challenging
task. Current methods mainly utilize NeRF-based methods to represent the static
scene and an additional time-variant MLP to model scene deformations, resulting
in relatively low rendering quality as well as slow inference speed. To tackle
these challenges, we propose a novel framework named Superpoint Gaussian
Splatting (SP-GS). Specifically, our framework first employs explicit 3D
Gaussians to reconstruct the scene and then clusters Gaussians with similar
properties (e.g., rotation, translation, and location) into superpoints.
Empowered by these superpoints, our method manages to extend 3D Gaussian
splatting to dynamic scenes with only a slight increase in computational
expense. Apart from achieving state-of-the-art visual quality and real-time
rendering under high resolutions, the superpoint representation provides a
stronger manipulation capability. Extensive experiments demonstrate the
practicality and effectiveness of our approach on both synthetic and real-world
datasets. Please see our project page at
this https URL

提出了一种名为 Superpoint Gaussian Splatting（SP-GS）的新框架，该框架通过使用显式的 3D 高斯函数来重构场景，并将具有相似属性的高斯函数聚类成超点，从而实现了对动态场景的实时渲染，获得了最新的视觉质量。