Abstract
The growing popularity of 3D Gaussian Splatting (3DGS) has intensified the need for effective copyright protection. Current 3DGS watermarking methods rely on computationally expensive finetuning 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.
Framework
Overview of our proposed method. The GaussianBridge module enables bi-directional transformation between 3D Gaussian Splatting (3DGS) models and Splatter Images. We propose novel 3DGS generalizable watermarking through a two-phase approach: a message embedder that applies a selective strategy to introduce targeted perturbations in the Splatter Image, and a message extractor that generates segmentation masks to precisely locate watermarked regions and retrieve the embedded messages.