ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting

TL;DR

ReorgGS reorganizes the distribution of Gaussian components in 3D Gaussian Splatting models to improve optimization and rendering quality by reducing parameter coupling and artifacts.

Contribution

It introduces ReorgGS, a novel method for reorganizing Gaussian distributions in 3D models, enhancing optimization and rendering without changing the scene support.

Findings

ReorgGS improves fitting quality at fixed Gaussian count.

It suppresses persistent floaters in the model.

ReorgGS reduces rendering overhead from redundant overlaps.

Abstract

A converged 3D Gaussian Splatting (3DGS) model may approximate the target scene while remaining poorly parameterized for further optimization. We identify this failure mode as \emph{parameterization degeneration}: high-opacity floaters attenuate gradients to true surfaces through alpha compositing, and redundant overlapping clusters create strongly coupled parameter blocks with nearly collinear Jacobian responses. These effects explain why continued optimization can plateau even when the model still contains removable artifacts. We propose ReorgGS, an equivalent distribution reorganization method for converged 3DGS models. ReorgGS treats the existing Gaussian set as an empirical probability field, resamples centers from it, estimates local anisotropic covariances with kNN, initializes low opacity, and continues optimization with the original 3DGS renderer and loss. Unlike opacity reset, which only rescales opacity on the old overlap graph, ReorgGS rebuilds centers, covariances, and visibility structure, thereby changing the graph itself. Our analysis shows that distributional equivalence is not optimization equivalence. The reorganized model preserves scene support while improving gradient accessibility under alpha compositing and reducing opacity-weighted overlap, thereby weakening local parameter coupling during subsequent optimization. Under the same additional optimization budget, ReorgGS improves fitting quality at a fixed Gaussian count, suppresses persistent floaters, and reduces rendering overhead from redundant overlap.