Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce Flux-GS, a way to create detailed 3D images quickly on mobile devices while using less memory and computing power. They use a special method to capture shiny lighting effects compactly without needing extra training. To keep fine details, they add a system that improves lighting representations without slowing down the process. They also improve how the 3D scene is built by checking from many viewpoints to avoid too many unnecessary parts. Experiments show their method keeps good image quality with fewer resources, making it useful for real-time rendering on phones.
3D Gaussian SplattingNovel View SynthesisSpherical HarmonicsMonte Carlo SamplingSpecular EnergyLatent SpaceCompressionMulti-view RenderingDensificationPruning
Authors
Xiaobiao Du, YuAn Wang, Hao Li, Bosheng Wang, Xun Sun, Xin Yu
Abstract
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: \textcolor{magenta}{\href{https://xiaobiaodu.github.io/flux-gs-project/}{https://xiaobiaodu.github.io/flux-gs-project/}}.