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. However, previous works fail to accurately reconstruct dynamic scenes, especially 1) static parts moving along nearby dynamic parts, and 2) some dynamic areas are blurry. We attribute the failure to the wrong 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 an efficient training strategy for faster convergence and higher quality. Project page: https://jeongminb.github.io/e-d3dgs/

翻译：三维高斯泼溅（3DGS）能够实现快速且高质量的新视角合成，因此将规范三维高斯泼溅变形至多帧是一种自然的扩展。然而，现有方法在准确重建动态场景方面存在不足，尤其是：1）静态部分随邻近动态部分移动；2）部分动态区域模糊。我们将这些不足归因于形变场的错误设计——其被构建为基于坐标的函数。该方式存在本质缺陷，因为三维高斯泼溅是由高斯中心处多个场的混合构成，而并非单一的基于坐标框架。为解决此问题，我们将形变定义为逐高斯嵌入与时间嵌入的函数。此外，我们将形变分解为粗形变和细形变，分别建模慢速与快速运动。同时，我们引入高效的训练策略以实现更快的收敛速度和更高质量。项目页面：https://jeongminb.github.io/e-d3dgs/