为3D高斯点云设计了抗局部盗用的原生水印方案
NGS-Marker: Robust Native Watermarking for 3D Gaussian Splatting
- 通过联合训练的注入器与解码器，实现全场景水印覆盖
- 在局部区域仍能准确解码版权信息，抵抗部分侵权
- 支持混合水印与多模态水印，适合实际部署
随着3D高斯点云（3DGS）的快速发展与广泛应用，版权保护需求日益迫切。现有3DGS水印技术主要依赖预训练解码器保护渲染图像，但对底层高斯原始数据的保护不足，尤其无法应对部分侵权问题——即攻击者仅提取并复用部分高斯点。本文提出NGS-Marker，一种针对3DGS的新型原生水印框架。该框架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，确保全场景覆盖，使任意局部区域均可可靠解码所有权信息。进一步扩展支持混合保护（原生+间接水印）与多模态水印。大量实验表明，NGS-Marker有效抵御部分侵权，同时具备实际部署的灵活性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。