cs.GRJun 3, 2026

Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting

Authors: Hongyu ZhouZorah Lähner

Organizations: University of Bonn, Germany · Lamarr Institut

Abstract

After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. However, extracting accurate geometric information directly from 3DGS remains challenging and can often reduce the appearance rendering quality. In this work, we show that 3DGS in its default form is inheritedly unsuited to represent texture and geometry at the same time, by training with complete ground-truth texture and geometry information. We also propose a simple solution by applying a single additional geometry opacity parameter to each splat, together with an optional transparency-curated optimization pipeline. Our experiments, both with ground-truth and vision foundation model geometric input, show that this change leads to improved rendering and geometry performance on a wide variety of dataset, and especially complex scenes with transparent objects benefit significantly from our method.

Explore similar work

CardsList
  1. Geometry-Aware Style Transfer in 3D Gaussian Splatting

    Jun 23, 2026Min Hyeok Bang, Jun Hyeong Kim, Seung-Wook Kim +13D Gaussian3D Geometry