RDSplat: 3D高斯散射中针对2D和3D扩散编辑的鲁棒水印
RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing
AI总结：
RDSplat是首个能抵御2D和3D扩散编辑的3D高斯散射水印框架，通过在低频高斯基元中嵌入100位水印，结合频率感知基元选择和替代策略，实现高效训练和强鲁棒性。
摘要：
3D高斯散射（3DGS）已成为高保真的3D资产表示方法，但通过数字水印保护这些资产仍是一个开放性挑战。现有3DGS水印方法仅对经典失真具有鲁棒性，但在扩散编辑下失效，后者在2D图像和3D场景层面操作，隐蔽地擦除嵌入的水印同时保持视觉合理性。我们提出了RDSplat，首个针对2D和3D扩散编辑的3DGS水印框架。我们的关键观察是扩散模型作为低通滤波器，保留低频结构并再生高频细节。RDSplat利用这一点，通过频率感知基元选择（FAPS）识别出的低频高斯基元嵌入100位水印，同时冻结其他基元。通过替代策略实现训练效率，用高斯模糊增强替代昂贵的扩散前向传递。专用解码器GeoMark基于ViT-S/16，结合空间周期性秘密嵌入，共同抵抗扩散编辑和新型视角渲染的几何变换。在四个基准和七种2D扩散攻击及迭代3D编辑下的大量实验表明，RDSplat在100位容量下具有强经典鲁棒性（位准确度0.811）和竞争性的扩散鲁棒性（位准确度0.701），在单个RTX 4090 GPU上完成微调仅需3到7分钟。
英文摘要：
3D Gaussian Splatting (3DGS) has become a leading representation for high-fidelity 3D assets, yet protecting these assets via digital watermarking remains an open challenge. Existing 3DGS watermarking methods are robust only to classical distortions and fail under diffusion editing, which operates at both the 2D image level and the 3D scene level, covertly erasing embedded watermarks while preserving visual plausibility. We present RDSplat, the first 3DGS watermarking framework designed to withstand both 2D and 3D diffusion editing. Our key observation is that diffusion models act as low-pass filters that preserve low-frequency structures while regenerating high-frequency details. RDSplat exploits this by embedding 100-bit watermarks exclusively into low-frequency Gaussian primitives identified through Frequency-Aware Primitive Selection (FAPS), which combines the Mip score and directional balance score, while freezing all other primitives. Training efficiency is achieved through a surrogate strategy that replaces costly diffusion forward passes with Gaussian blur augmentation. A dedicated decoder, GeoMark, built on ViT-S/16 with spatially periodic secret embedding, jointly resists diffusion editing and the geometric transformations inherent to novel-view rendering. Extensive experiments on four benchmarks under seven 2D diffusion attacks and iterative 3D editing demonstrate strong classical robustness (bit accuracy 0.811) and competitive diffusion robustness (bit accuracy 0.701) at 100-bit capacity, while completing fine-tuning in 3 to 7 minutes on a single RTX 4090 GPU.
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。
