arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.05047quant-phcs.CV
收藏

QuantumGS: 用于高斯点云的量子编码框架

QuantumGS: Quantum Encoding Framework for Gaussian Splatting

Jagiellonian University(雅盖隆大学);IDEAS Research Institute(IDEAS研究 institutes)

Grzegorz Wilczyński, Rafał Tobiasz, Paweł Gora, Marcin Mazur, Przemysław Spurek

AI总结:

QuantumGS通过引入量子电路提升高斯点云在高频率视点依赖效果捕捉中的表现,实现更高表达能力和泛化能力。

摘要:

近年来,神经渲染领域,特别是三维高斯点云(3DGS)的进步,使复杂场景的实时渲染成为可能。然而,标准的3DGS依赖于球谐函数,这往往难以准确捕捉高频视点依赖效果,如锐利的反射和透明度。尽管混合方法如视点方向高斯点云(VDGS)通过使用经典多层感知机(MLP)来缓解这一限制,但它们仍然受限于经典网络在低参数情况下表达能力的不足。在本文中,我们引入了QuantumGS,一种新的混合框架,将变分量子电路(VQC)整合到高斯点云流程中。我们提出了一种独特的编码策略,将视点方向直接映射到布洛赫球上,利用量子比特的自然几何特性来表示三维方向数据。通过将经典颜色调节网络替换为通过超网络或条件机制生成的量子电路,我们实现了更高的表达能力和更好的泛化能力。源代码可在补充材料中提供。代码可在https://github.com/gwilczynski95/QuantumGS获取。

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑