发表机构
Zhejiang University; Zhejiang Key Laboratory of Geographic Information Science（浙江大学; 浙江省地理信息科学重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对现有3D高斯溅射水印技术无法抵御部分侵权的问题，提出NGS-Marker原生水印框架，通过联合训练的注入器与解码器及梯度渐进注入策略实现全场景覆盖，可抵御部分侵权并支持混合与多模态水印，具备实际部署灵活性。
AI 中文摘要
随着3D高斯溅射（3DGS）的快速发展与应用，有效的版权保护需求日益关键。现有针对3DGS的水印技术主要通过预训练解码器保护渲染图像，却未顾及底层3D高斯基元易被滥用的问题，尤其对仅提取并复用部分高斯的部分侵权攻击无效。本文提出一种针对3DGS的新型原生水印框架NGS-Marker，它集成联合训练的水印注入器与消息解码器，并采用基于梯度的渐进式注入策略以实现全场景覆盖，从而支持从任意局部区域进行可靠的所有权解码。我们还为NGS-Marker扩展了混合保护（结合原生与间接水印）及多模态水印支持。大量实验表明，NGS-Marker可有效抵御部分侵权，同时为实际部署提供实用灵活性。
英文摘要
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.
