GPS-Gaussian：通用像素级3D高斯飞溅用于实时人类新视角合成

摘要

我们提出了一种名为GPS-Gaussian的新方法，用于以实时方式合成角色的新视图。所提出的方法在稀疏视图相机设置下实现了2K分辨率渲染。与原始的高斯点渲染或神经隐式渲染方法不同，这些方法需要对每个主体进行优化，我们引入了在源视图上定义的高斯参数图，并直接回归高斯点渲染属性，以便立即合成新视图，无需任何微调或优化。为此，我们在大量人体扫描数据上训练我们的高斯参数回归模块，同时结合深度估计模块将2D参数图提升到3D空间。所提出的框架是完全可微的，对几个数据集的实验表明，我们的方法在实现超越渲染速度的同时优于最先进的方法。

English

We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner. The proposed method enables 2K-resolution rendering under a sparse-view camera setting. Unlike the original Gaussian Splatting or neural implicit rendering methods that necessitate per-subject optimizations, we introduce Gaussian parameter maps defined on the source views and regress directly Gaussian Splatting properties for instant novel view synthesis without any fine-tuning or optimization. To this end, we train our Gaussian parameter regression module on a large amount of human scan data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. The proposed framework is fully differentiable and experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.

GPS-Gaussian：通用像素级3D高斯飞溅用于实时人类新视角合成

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

摘要

Support