为3D高斯点云设计了隐秘版权水印技术，防止盗用且不破坏视觉效果。
GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
- 基于不确定性约束扰动参数，实现不可见水印嵌入。
- 在多种三维和二维失真下仍能准确提取版权信息。
- 适用于3D高斯点云版权保护，适合数字资产创作者使用。
3D高斯点云（3DGS）已成为获取3D资产的关键方法。为保护这些资产的版权，可采用数字水印技术将所有权信息隐蔽嵌入3DGS模型中。然而，现有针对网格、点云和隐式辐射场的水印方法无法直接应用于3DGS模型，因其采用显式3D高斯分布结构，且不依赖神经网络。在预训练3DGS上直接嵌入水印会导致渲染图像明显失真。为此，本文提出一种基于不确定性的方法，通过约束模型参数扰动，实现3DGS的不可见水印。在解码阶段，即使面对各种3D和2D失真，仍可从3D高斯分布和2D渲染图像中可靠提取版权信息。我们在Blender、LLFF和MipNeRF-360数据集上进行了大量实验，验证了所提方法在消息解码准确率和视图合成质量方面均达到当前最优水平。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) has become a crucial method for acquiring 3D assets. To protect the copyright of these assets, digital watermarking techniques can be applied to embed ownership information discreetly within 3DGS models. However, existing watermarking methods for meshes, point clouds, and implicit radiance fields cannot be directly applied to 3DGS models, as 3DGS models use explicit 3D Gaussians with distinct structures and do not rely on neural networks. Naively embedding the watermark on a pre-trained 3DGS can cause obvious distortion in rendered images. In our work, we propose an uncertainty-based method that constrains the perturbation of model parameters to achieve invisible watermarking for 3DGS. At the message decoding stage, the copyright messages can be reliably extracted from both 3D Gaussians and 2D rendered images even under various forms of 3D and 2D distortions. We conduct extensive experiments on the Blender, LLFF and MipNeRF-360 datasets to validate the effectiveness of our proposed method, demonstrating state-of-the-art performance on both message decoding accuracy and view synthesis quality.
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。