HaloGS: Loose Coupling of Compact Geometry and Gaussian Splats for 3D Scenes

TL;DR

HaloGS introduces a dual representation combining coarse triangles for geometry and Gaussian primitives for appearance, achieving a compact, efficient, and high-fidelity 3D reconstruction and rendering suitable for diverse environments.

Contribution

It presents a novel loose coupling of geometry and appearance representations, balancing efficiency and fidelity in 3D scene reconstruction.

Findings

Produces compact and accurate geometry.

Delivers photo-realistic rendering across various scenes.

Outperforms existing methods on benchmark datasets.

Abstract

High fidelity 3D reconstruction and rendering hinge on capturing precise geometry while preserving photo realistic detail. Most existing methods either fuse these goals into a single cumbersome model or adopt hybrid schemes whose uniform primitives lead to a trade off between efficiency and fidelity. In this paper, we introduce HaloGS, a dual representation that loosely couples coarse triangles for geometry with Gaussian primitives for appearance, motivated by the lightweight classic geometry representations and their proven efficiency in real world applications. Our design yields a compact yet expressive model capable of photo realistic rendering across both indoor and outdoor environments, seamlessly adapting to varying levels of scene complexity. Experiments on multiple benchmark datasets demonstrate that our method yields both compact, accurate geometry and high fidelity renderings, especially in challenging scenarios where robust geometric structure make a clear difference.