NGS-Marker: Robust Native Watermarking for 3D Gaussian Splatting

2026-08-18

AI Summary

为解决3D高斯点云版权保护问题，提出NGS-Marker框架，采用联合训练的水印注入与解码器及基于梯度的渐进注入策略，有效防御部分侵权。

Abstract

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.

Problem

• 3D Gaussian Splatting
• watermarking
• partial infringement
• copyright protection

Innovation

• NGS-Marker
• Gradient-based Progressive Injection
• Hybrid Protection
• Multimodal Watermarking