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.

翻译：我们提出一种名为GPS-Gaussian的新方法，用于在实时场景下合成角色的新视角。该方法支持稀疏相机设置下的2K分辨率渲染。与需要逐对象优化的原始高斯泼溅或神经隐式渲染方法不同，我们引入在源视角上定义的高斯参数图，并直接回归高斯泼溅属性，无需任何微调或优化即可实现即时新视角合成。为此，我们在大量人体扫描数据上训练高斯参数回归模块，同时结合深度估计模块将二维参数图提升至三维空间。所提出的框架完全可微分，多数据集实验表明，本方法在实现极致渲染速度的同时，性能优于当前最先进方法。