Search papers, labs, and topics across Lattice.
This paper introduces NGS-Marker, a robust watermarking framework specifically designed for 3D Gaussian Splatting (3DGS) to protect against copyright infringement, particularly focusing on the vulnerability of 3D Gaussian primitives. By employing a gradient-based progressive injection strategy alongside a jointly trained watermark injector and message decoder, NGS-Marker ensures comprehensive coverage and effective ownership decoding from any local region. Experimental results show that NGS-Marker significantly mitigates the risks of partial infringement while maintaining practical flexibility for real-world applications.
NGS-Marker effectively thwarts partial infringement in 3D Gaussian Splatting, ensuring robust copyright protection for 3D assets.
With the rapid development and adoption of 3D Gaussian Splatting (3DGS), the need for effective copyright protection has become increasingly critical. Existing watermarking techniques for 3DGS mainly focus on protecting rendered images via pre-trained decoders, leaving the underlying 3D Gaussian primitives vulnerable to misuse. In particular, they are ineffective against Partial Infringement, where an adversary extracts and reuses only a subset of Gaussians. In this paper, we propose NGS-Marker, a novel native watermarking framework for 3DGS. It integrates a jointly trained watermark injector and message decoder, and employs a gradientbased progressive injection strategy to ensure full-scene coverage. This enables robust ownership decoding from any local region. We further extend NGS-Marker with hybrid protection (combining native and indirect watermarks) and support for multimodal watermarking. Extensive experiments demonstrate that NGS-Marker effectively defends against partial infringement while offering practical flexibility for real-world deployment.
