水印能否保护3D高斯散射的版权？
Can Protective Watermarking Safeguard the Copyright of 3D Gaussian Splatting?
AI总结：
本文首次系统研究并验证了3D高斯散射水印框架的潜在漏洞，提出GSPure框架有效去除水印并保持场景完整性，实验表明其在水印净化性能上优于现有方法。
摘要：
3D高斯散射（3DGS）作为一种强大的3D场景表示方法，因其高效性和高保真的视觉质量而被广泛应用。鉴于3DGS资产的重要价值，近期研究引入了专门的水印方案以确保版权保护和所有权验证。然而，现有3D高斯水印方法是否能真正保证3D资产的鲁棒保护？本文首次系统探索并验证了3DGS水印框架的潜在漏洞。我们证明，传统的2D图像水印移除技术无法有效推广到3DGS场景，因为其专用的渲染管道和每个高斯原始体的独特属性。受此启发，我们提出了GSPure，首个专门针对3DGS水印表示的水印净化框架。通过分析视图依赖的渲染贡献并利用几何准确的特征聚类，GSPure精确隔离并有效移除与水印相关的高斯原始体，同时保持场景完整性。大量实验表明，我们的GSPure在水印净化性能上表现最佳，将水印PSNR降低高达16.34dB，同时最小化对原始场景保真度的降级，PSNR损失低于1dB。此外，它在有效性和泛化性上均优于现有方法。我们的代码可在https://github.com/insightlab-CG-3DV/GSPure上获得。
英文摘要：
3D Gaussian Splatting (3DGS) has emerged as a powerful representation for 3D scenes, widely adopted due to its exceptional efficiency and high-fidelity visual quality. Given the significant value of 3DGS assets, recent works have introduced specialized watermarking schemes to ensure copyright protection and ownership verification. However, can existing 3D Gaussian watermarking approaches genuinely guarantee robust protection of the 3D assets? In this paper, for the first time, we systematically explore and validate possible vulnerabilities of 3DGS watermarking frameworks. We demonstrate that conventional watermark removal techniques designed for 2D images do not effectively generalize to the 3DGS scenario due to the specialized rendering pipeline and unique attributes of each gaussian primitives. Motivated by this insight, we propose GSPure, the first watermark purification framework specifically for 3DGS watermarking representations. By analyzing view-dependent rendering contributions and exploiting geometrically accurate feature clustering, GSPure precisely isolates and effectively removes watermark-related Gaussian primitives while preserving scene integrity. Extensive experiments demonstrate that our GSPure achieves the best watermark purification performance, reducing watermark PSNR by up to 16.34dB while minimizing degradation to original scene fidelity with less than 1dB PSNR loss. Moreover, it consistently outperforms existing methods in both effectiveness and generalization. Our code is available at https://github.com/insightlab-CG-3DV/GSPure.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
