3D-GSW: 3D Gaussian Splatting for Robust Watermarking

2024-09-20

AI Summary

To address copyright protection challenges for 3D Gaussian Splatting (3D-GS) models and their rendered images, this paper proposes the first dual-domain robust watermarking method jointly securing both the model and image domains. Our approach introduces Frequency-Guided Densification (FGD), leveraging Fourier-domain analysis to selectively prune high-contribution Gaussians while preserving rendering fidelity. We further design a 3D Gaussian gradient mask and a wavelet subband loss function to jointly optimize watermark imperceptibility, rendering quality, and robustness. The method demonstrates strong resilience against diverse attacks—including rendering distortions, model tampering, and geometric, lighting, and cropping perturbations—achieving significantly higher PSNR and SSIM than existing baselines. Moreover, it improves real-time rendering efficiency by 12.6%, enabling practical deployment without compromising security or visual quality.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

As 3D Gaussian Splatting (3D-GS) gains significant attention and its commercial usage increases, the need for watermarking technologies to prevent unauthorized use of the 3D-GS models and rendered images has become increasingly important. In this paper, we introduce a robust watermarking method for 3D-GS that secures copyright of both the model and its rendered images. Our proposed method remains robust against distortions in rendered images and model attacks while maintaining high rendering quality. To achieve these objectives, we present Frequency-Guided Densification (FGD), which removes 3D Gaussians based on their contribution to rendering quality, enhancing real-time rendering and the robustness of the message. FGD utilizes Discrete Fourier Transform to split 3D Gaussians in high-frequency areas, improving rendering quality. Furthermore, we employ a gradient mask for 3D Gaussians and design a wavelet-subband loss to enhance rendering quality. Our experiments show that our method embeds the message in the rendered images invisibly and robustly against various attacks, including model distortion. Our method achieves superior performance in both rendering quality and watermark robustness while improving real-time rendering efficiency. Project page: https://kuai-lab.github.io/cvpr20253dgsw/

Problem

• Develop robust watermarking for 3D Gaussian Splatting models
• Secure copyright of 3D-GS models and rendered images
• Maintain rendering quality while resisting distortions and attacks

Innovation

• Frequency-Guided Densification for robust watermarking
• Discrete Fourier Transform enhances rendering quality
• Wavelet-subband loss improves watermark robustness