Splats in Splats: Robust and Effective 3D Steganography towards Gaussian Splatting

TL;DR

This paper introduces a novel 3D steganography method for Gaussian splatting that embeds hidden content without altering scene attributes, enhancing copyright protection while maintaining high fidelity and efficiency.

Contribution

It presents the first 3DGS steganography framework using spherical harmonics and autoencoders, improving security, robustness, and performance over existing techniques.

Findings

5.31% higher scene fidelity

3x faster rendering speed

outperforms existing 3D steganography methods

Abstract

3D Gaussian splatting (3DGS) has demonstrated impressive 3D reconstruction performance with explicit scene representations. Given the widespread application of 3DGS in 3D reconstruction and generation tasks, there is an urgent need to protect the copyright of 3DGS assets. However, existing copyright protection techniques for 3DGS overlook the usability of 3D assets, posing challenges for practical deployment. Here we describe splats in splats, the first 3DGS steganography framework that embeds 3D content in 3DGS itself without modifying any attributes. To achieve this, we take a deep insight into spherical harmonics (SH) and devise an importance-graded SH coefficient encryption strategy to embed the hidden SH coefficients. Furthermore, we employ a convolutional autoencoder to establish a mapping between the original Gaussian primitives' opacity and the hidden Gaussian primitives' opacity. Extensive experiments indicate that our method significantly outperforms existing 3D steganography techniques, with 5.31% higher scene fidelity and 3x faster rendering speed, while ensuring security, robustness, and user experience.