A two-level 2D Gaussian splatting method with direct covariance optimization fits large images with more Gaussian points and higher PSNR than prior Gaussian-based image representation.
Mathematical Supplement for the $\texttt{gsplat}$ Library
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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 .
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting
A two-level 2D Gaussian splatting method with direct covariance optimization fits large images with more Gaussian points and higher PSNR than prior Gaussian-based image representation.