As 3D Gaussian Splatting (3DGS) provides fast and high-quality novel view synthesis, it is a natural extension to deform a canonical 3DGS to multiple frames for representing a dynamic scene. However, previous works fail to accurately reconstruct complex dynamic scenes. We attribute the failure to the design of the deformation field, which is built as a coordinate-based function. This approach is problematic because 3DGS is a mixture of multiple fields centered at the Gaussians, not just a single coordinate-based framework. To resolve this problem, we define the deformation as a function of per-Gaussian embeddings and temporal embeddings. Moreover, we decompose deformations as coarse and fine deformations to model slow and fast movements, respectively. Also, we introduce a local smoothness regularization for per-Gaussian embedding to improve the details in dynamic regions. Project page: https://jeongminb.github.io/e-d3dgs/

翻译：随着3D高斯泼溅（3DGS）能够实现快速且高质量的新视角合成，将规范3DGS变形至多帧以表示动态场景成为一种自然的扩展。然而，先前的工作未能准确重建复杂的动态场景。我们将此失败归因于变形场的设计，该变形场被构建为基于坐标的函数。这种方法存在问题，因为3DGS是以高斯分布为中心的多个场的混合体，而不仅仅是一个单一的基于坐标的框架。为了解决这个问题，我们将变形定义为逐高斯嵌入和时序嵌入的函数。此外，我们将变形分解为粗变形和细变形，分别用于建模缓慢和快速的运动。同时，我们为逐高斯嵌入引入了局部平滑正则化，以改善动态区域的细节。项目页面：https://jeongminb.github.io/e-d3dgs/