QuantumGS: Quantum Encoding Framework for Gaussian Splatting

TL;DR

QuantumGS introduces a hybrid quantum-classical framework for neural rendering that enhances the modeling of view-dependent effects in 3D Gaussian Splatting by leveraging quantum encoding of viewing directions.

Contribution

It proposes a novel quantum encoding strategy and integrates variational quantum circuits into the Gaussian Splatting pipeline, improving expressivity over classical methods.

Findings

Enhanced rendering of high-frequency view-dependent effects

Higher expressivity with quantum circuits compared to classical networks

Open-source implementation available

Abstract

Recent advances in neural rendering, particularly 3D Gaussian Splatting (3DGS), have enabled real-time rendering of complex scenes. However, standard 3DGS relies on spherical harmonics, which often struggle to accurately capture high-frequency view-dependent effects such as sharp reflections and transparency. While hybrid approaches like Viewing Direction Gaussian Splatting (VDGS) mitigate this limitation using classical Multi-Layer Perceptrons (MLPs), they remain limited by the expressivity of classical networks in low-parameter regimes. In this paper, we introduce QuantumGS, a novel hybrid framework that integrates Variational Quantum Circuits (VQC) into the Gaussian Splatting pipeline. We propose a unique encoding strategy that maps the viewing direction directly onto the Bloch sphere, leveraging the natural geometry of qubits to represent 3D directional data. By replacing classical color-modulating networks with quantum circuits generated via a hypernetwork or conditioning mechanism, we achieve higher expressivity and better generalization. Source code is available in the supplementary material. Code is available at https://github.com/gwilczynski95/QuantumGS