The reviewed record of science sign in
Pith

arxiv: 2312.02121 · v1 · pith:COPQB2NC · submitted 2023-12-04 · cs.MS · cs.CV· cs.GR· cs.NA· math.NA

Mathematical Supplement for the texttt{gsplat} Library

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:COPQB2NCrecord.jsonopen to challenge →

classification cs.MS cs.CVcs.GRcs.NAmath.NA
keywords gsplatbackwarddifferentiableforwardgaussianlibrarymathematicalpasses
0
0 comments X
read the original 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 .

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.