Mathematical Supplement for the $\texttt{gsplat}$ Library
It supports developers and researchers working on differentiable Gaussian splatting by documenting the underlying mathematics for practical implementation.
This report provides mathematical details for the gsplat library, a toolbox for efficient differentiable Gaussian splatting, offering a self-contained reference for forward and backward pass computations.
This report provides the mathematical details of the gsplat library, a modular toolbox for efficient differentiable Gaussian splatting, as proposed by Kerbl et al. It provides a self-contained reference for the computations involved in the forward and backward passes of differentiable Gaussian splatting. To facilitate practical usage and development, we provide a user friendly Python API that exposes each component of the forward and backward passes in rasterization at github.com/nerfstudio-project/gsplat .