Paper page - Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting

Source: https://huggingface.co/papers/2606.30017 Published on Jun 29

·

Submitted byhttps://huggingface.co/xiaobiaodu

Duon Jun 30

Abstract

Flux-GS enables real-time high-fidelity 3D Gaussian Splatting on mobile platforms through efficient lighting representation, attribute-conditioned enhancement, and multi-view densification strategies.

Recent advances in 3DGaussian Splattinghave demonstrated unprecedented success in novel view synthesis. However, the substantial inference and storage overhead driven by high-orderSpherical Harmonics(SH) are primary bottlenecks formobile platforms. In this paper, we present Flux-GS, a real-timeGaussian Splattingmethod designed to achieve high-fidelity rendering with significantly reduced overhead for resource-constrainedmobile platforms. We first propose aMonte Carlo Specular Energy Aggregator, sampling third-order radiance residuals and aggregating specular energy into a compactlatent 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 anAttribute-Conditioned SH Enhancementmodule. 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 andPruningstrategy. 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/}}.

View arXiv pageView PDFProject pageGitHub0Add to collection

Get this paper in your agent:

hf papers read 2606\.30017

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.30017 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.30017 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.30017 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.