GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Model
This addresses copyright protection for 3D object generative models, a domain with little prior exploration, though it is incremental as it adapts existing watermarking concepts to a new modality.
The paper tackles the problem of copyright protection for 3D Gaussian Splatting generative models by proposing GaussianSeal, the first bit watermarking framework, which achieves high-precision bit decoding from rendered outputs while maintaining output fidelity.
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.