为3D高斯模型设计自适应水印，实现版权标识精准提取
GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Model
- 在生成网络中嵌入自适应比特调制模块，动态调节水印强度
- 水印解码准确率高，训练开销小，生成结果质量几乎不受影响
- 首个针对3D高斯点云生成模型的比特级水印框架，适合版权保护场景
随着AIGC技术发展，生成模态从图像、视频扩展到3D物体，相关研究日益增多。现有版权保护工作主要集中于图像与文本模态，对3D物体生成模型的版权保护研究较少。本文提出首个针对3D高斯点云生成模型（3DGS）的比特水印框架GaussianSeal，可从生成结果的渲染输出中解码出比特形式的版权标识。通过将自适应比特调制模块嵌入生成模型的网络块中，实现高精度比特解码，且训练开销极小，同时保持模型输出的高质量。实验表明，该方法优于后处理水印方案，在水印解码准确率和生成质量保留方面均表现更优。
原文摘要 · Abstract (English)
With the advancement of AIGC technologies, the modalities generated by models have expanded from images and videos to 3D objects, leading to an increasing number of works focused on 3D Gaussian Splatting (3DGS) generative models. Existing research on copyright protection for generative models has primarily concentrated on watermarking in image and text modalities, with little exploration into the copyright protection of 3D object generative models. In this paper, we propose the first bit watermarking framework for 3DGS generative models, named GaussianSeal, to enable the decoding of bits as copyright identifiers from the rendered outputs of generated 3DGS. By incorporating adaptive bit modulation modules into the generative model and embedding them into the network blocks in an adaptive way, we achieve high-precision bit decoding with minimal training overhead while maintaining the fidelity of the model's outputs. Experiments demonstrate that our method outperforms post-processing watermarking approaches for 3DGS objects, achieving superior performance of watermark decoding accuracy and preserving the quality of the generated results.
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。