arXiv:2604.15862cs.CV2026-04

在3D高斯点云中隐藏信息,既不破坏视觉效果又抗攻击。

Splats in Splats++: Robust and Generalizable 3D Gaussian Splatting Steganography

论文配图:Splats in Splats++: Robust and Generalizable 3D Gaussian Splatting Steganography
图 1 · 摘自论文原文
  • 基于球谐函数重要性分级加密,实现无感知嵌入。
  • 消息保真度提升6.28分贝,渲染速度加快三倍。
  • 适合版权保护、动态场景隐写,通用性强。

3D高斯点云(3DGS)近期重新定义了3D重建范式,在视觉保真度与计算效率之间取得了前所未有的平衡。随着其广泛应用,显式3DGS资产的版权保护变得至关重要。然而,现有不可见信息嵌入框架难以兼顾安全、高容量嵌入与原始资产可用性,常破坏原生渲染流程或对结构扰动敏感。本文提出 extbf{ extit{Splats in Splats++}},一种统一且流程无关的隐写框架,可直接在原生3DGS表示中嵌入高容量3D/4D内容。基于球谐函数(SH)频率分布的原理分析,提出重要性分级的SH系数加密方案,实现无感知嵌入且不损失原有表达能力。为根本解决导致信息泄露的几何歧义,引入 extbf{哈希网格引导的透明度映射}机制,并设计新颖的 extbf{梯度门控透明度一致性损失},强制原场景与隐藏场景间严格的时空属性耦合,将离散属性映射投影至连续、抗攻击的潜在流形。大量实验表明,本方法显著优于现有方法:消息保真度最高提升6.28分贝,渲染速度加快3倍,对强3D目标结构攻击(如GSPure)具有极强鲁棒性。此外,该框架具备出色泛化能力,可无缝应用于2D图像隐写、4D动态场景隐写及多种下游任务。

原文摘要 · Abstract (English)

3D Gaussian Splatting (3DGS) has recently redefined the paradigm of 3D reconstruction, striking an unprecedented balance between visual fidelity and computational efficiency. As its adoption proliferates, safeguarding the copyright of explicit 3DGS assets has become paramount. However, existing invisible message embedding frameworks struggle to reconcile secure and high-capacity data embedding with intrinsic asset utility, often disrupting the native rendering pipeline or exhibiting vulnerability to structural perturbations. In this work, we present \textbf{\textit{Splats in Splats++}}, a unified and pipeline-agnostic steganography framework that seamlessly embeds high-capacity 3D/4D content directly within the native 3DGS representation. Grounded in a principled analysis of the frequency distribution of Spherical Harmonics (SH), we propose an importance-graded SH coefficient encryption scheme that achieves imperceptible embedding without compromising the original expressive power. To fundamentally resolve the geometric ambiguities that lead to message leakage, we introduce a \textbf{Hash-Grid Guided Opacity Mapping} mechanism. Coupled with a novel \textbf{Gradient-Gated Opacity Consistency Loss}, our formulation enforces a stringent spatial-attribute coupling between the original and hidden scenes, effectively projecting the discrete attribute mapping into a continuous, attack-resilient latent manifold. Extensive experiments demonstrate that our method substantially outperforms existing approaches, achieving up to \textbf{6.28 db} higher message fidelity, \textbf{3$\times$} faster rendering, and exceptional robustness against aggressive 3D-targeted structural attacks (e.g., GSPure). Furthermore, our framework exhibits remarkable versatility, generalizing seamlessly to 2D image embedding, 4D dynamic scene steganography, and diverse downstream tasks.

3D生成隐写术高斯点云版权保护

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。