MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure
This addresses the need for efficient and scalable watermarking in 3DGS models, offering a practical solution for content creators, though it is incremental as it builds on existing Splatter Image structures.
The paper tackles the problem of copyright protection for 3D Gaussian Splatting models by proposing a generalizable watermarking framework that embeds arbitrary messages efficiently in a single forward pass, achieving robust extraction with minimal visual impact.
The growing popularity of 3D Gaussian Splatting (3DGS) has intensified the need for effective copyright protection. Current 3DGS watermarking methods rely on computationally expensive fine-tuning procedures for each predefined message. We propose the first generalizable watermarking framework that enables efficient protection of Splatter Image-based 3DGS models through a single forward pass. We introduce GaussianBridge that transforms unstructured 3D Gaussians into Splatter Image format, enabling direct neural processing for arbitrary message embedding. To ensure imperceptibility, we design a Gaussian-Uncertainty-Perceptual heatmap prediction strategy for preserving visual quality. For robust message recovery, we develop a dense segmentation-based extraction mechanism that maintains reliable extraction even when watermarked objects occupy minimal regions in rendered views. Project page: https://kevinhuangxf.github.io/marksplatter.