Mobile-GS：面向移动设备的实时高斯泼溅渲染技术

Mobile-GS: Real-time Gaussian Splatting for Mobile Devices

March 12, 2026

作者: Xiaobiao Du, Yida Wang, Kun Zhan, Xin Yu

cs.AI

摘要

3D高斯泼溅（3DGS）作为一种强大的表示方法，已在广泛应用中实现高质量渲染。然而，其高计算需求和大存储成本给移动设备部署带来了巨大挑战。本研究提出一种面向移动端的实时高斯泼溅方法Mobile-GS，可在边缘设备上实现高效推理。具体而言，我们首先发现阿尔法混合是主要计算瓶颈，因其依赖耗时的高斯深度排序过程。为此，我们提出深度感知的无序渲染方案，通过消除排序需求显著加速渲染。虽然无序渲染提升了速度，但可能因渲染顺序缺失在几何重叠区域产生透明伪影。针对该问题，我们提出神经视角依赖增强策略，基于观察方向、3D高斯几何和外观属性实现更精确的视角依赖效果建模。由此，Mobile-GS可同时实现高质量与实时渲染。此外，为促进在内存受限的移动平台部署，我们引入一阶球谐蒸馏、神经向量量化技术及基于贡献度的剪枝策略，借助神经网络减少高斯图元数量并压缩3D高斯表示。大量实验表明，Mobile-GS在保持高视觉质量的同时实现了实时渲染与紧凑模型尺寸，非常适合移动应用场景。

English

3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-quality rendering across a wide range of applications.However, its high computational demands and large storage costs pose significant challenges for deployment on mobile devices. In this work, we propose a mobile-tailored real-time Gaussian Splatting method, dubbed Mobile-GS, enabling efficient inference of Gaussian Splatting on edge devices. Specifically, we first identify alpha blending as the primary computational bottleneck, since it relies on the time-consuming Gaussian depth sorting process. To solve this issue, we propose a depth-aware order-independent rendering scheme that eliminates the need for sorting, thereby substantially accelerating rendering. Although this order-independent rendering improves rendering speed, it may introduce transparency artifacts in regions with overlapping geometry due to the scarcity of rendering order. To address this problem, we propose a neural view-dependent enhancement strategy, enabling more accurate modeling of view-dependent effects conditioned on viewing direction, 3D Gaussian geometry, and appearance attributes. In this way, Mobile-GS can achieve both high-quality and real-time rendering. Furthermore, to facilitate deployment on memory-constrained mobile platforms, we also introduce first-order spherical harmonics distillation, a neural vector quantization technique, and a contribution-based pruning strategy to reduce the number of Gaussian primitives and compress the 3D Gaussian representation with the assistance of neural networks. Extensive experiments demonstrate that our proposed Mobile-GS achieves real-time rendering and compact model size while preserving high visual quality, making it well-suited for mobile applications.