In recent years, a range of neural network-based methods for image rendering
have been introduced. For instance, widely-researched neural radiance fields
(NeRF) rely on a neural network to represent 3D scenes, allowing for realistic
view synthesis from a small number of 2D images. However, most NeRF models are
constrained by long training and inference times. In comparison, Gaussian
Splatting (GS) is a novel, state-of-theart technique for rendering points in a
3D scene by approximating their contribution to image pixels through Gaussian
distributions, warranting fast training and swift, real-time rendering. A
drawback of GS is the absence of a well-defined approach for its conditioning
due to the necessity to condition several hundred thousand Gaussian components.
To solve this, we introduce Gaussian Mesh Splatting (GaMeS) model, a hybrid of
mesh and a Gaussian distribution, that pin all Gaussians splats on the object
surface (mesh). The unique contribution of our methods is defining Gaussian
splats solely based on their location on the mesh, allowing for automatic
adjustments in position, scale, and rotation during animation. As a result, we
obtain high-quality renders in the real-time generation of high-quality views.
Furthermore, we demonstrate that in the absence of a predefined mesh, it is
possible to fine-tune the initial mesh during the learning process.

最近几年，引入了一系列基于神经网络的图像渲染方法。其中，被广泛研究的神经辐射场（NeRF）依靠神经网络来表示三维场景，可以从少量的二维图像中合成逼真的视图。然而，大多数 NeRF 模型在训练和推理时间上都受到限制。相比之下，高斯喷洒（GS）是一种新颖的、领先技术的渲染点的技术，通过高斯分布来近似它们对图像像素的贡献，从而保证快速训练和实时渲染。GS 的一个缺点是缺乏对其条件的明确定义，因为需要对几十万个高斯分量进行条件建模。为了解决这个问题，我们引入了高斯网格喷洒（GaMeS）模型，它是网格和高斯分布的混合形式，在物体表面（网格）上固定所有高斯喷洒。我们方法的独特之处在于，仅根据高斯喷洒在网格上的位置来定义，允许在动画过程中自动调整位置、比例和旋转。因此，我们实现了在实时生成高质量视图方面的高质量渲染。此外，我们证明在没有预定义网格的情况下，可以在学习过程中调整初始网格。