移动端三维高斯泼溅的蒙特卡洛能量聚合

摘要

近年来，3D高斯泼溅在新视角合成领域取得了前所未有的成功。然而，高阶球谐函数带来的庞大推理与存储开销成为移动平台的主要瓶颈。本文提出Flux-GS——一种面向资源受限移动平台、可实现高保真渲染并显著降低开销的实时高斯泼溅方法。我们首先提出蒙特卡洛镜面能量聚合器，通过采样三阶辐射残差并将镜面能量压缩至紧凑隐空间。该方法能在无需高昂蒸馏或预训练的情况下，有效保留低阶频段中视觉显著的照明特征。为弥补压缩过程中损失的高频细节，我们引入属性自适应球谐增强模块：该模块基于高斯固有属性预测高斯感知偏移量，在推理前增强一阶球谐表示，且不增加额外推理成本。此外，原始单视图梯度驱动致密化策略易产生过量高斯体并导致特定视角过拟合。我们通过提出多视图α驱动致密化与剪枝策略解决上述局限，借助多视图引导确保结构一致性并精确移除冗余基元。大量实验表明，Flux-GS在保持竞争力视觉质量的同时实现大幅参数压缩，为移动端实时渲染提供了稳健且可扩展的解决方案。代码：magenta{https://xiaobiaodu.github.io/flux-gs-project/{https://xiaobiaodu.github.io/flux-gs-project/}}。

English

Recent advances in 3D Gaussian Splatting have demonstrated unprecedented success in novel view synthesis. However, the substantial inference and storage overhead driven by high-order Spherical Harmonics (SH) are primary bottlenecks for mobile platforms. In this paper, we present Flux-GS, a real-time Gaussian Splatting method designed to achieve high-fidelity rendering with significantly reduced overhead for resource-constrained mobile platforms. We first propose a Monte Carlo Specular Energy Aggregator, sampling third-order radiance residuals and aggregating specular energy into a compact latent space. In this way, our method effectively preserves visually salient lighting features in lower-order bands without expensive distillation or pre-training. To mitigate the high-frequency details lost during compression, we introduce an Attribute-Conditioned SH Enhancement module. This module predicts Gaussian-aware offsets based on intrinsic Gaussian attributes, which enhance the first-order SH representation prior to inference, without extra inference costs. Furthermore, the original single-view gradient-based densification is prone to producing excessive Gaussians and overfitting to a certain view. We address these limitations by proposing a Multi-view Alpha-based Densification and Pruning strategy. By leveraging multi-view guidance, we ensure multi-view structure consistency and the precise removal of redundant primitives. Extensive experiments demonstrate that Flux-GS achieves substantial parameter reduction while maintaining competitive visual quality, offering a robust and scalable solution for real-time mobile rendering. Code: magenta{https://xiaobiaodu.github.io/flux-gs-project/{https://xiaobiaodu.github.io/flux-gs-project/}}.