Mark4D：面向4D高斯泼溅的时序一致水印技术
Mark4D: Temporally-Consistent Watermarking for 4D Gaussian Splatting
针对动态4D高斯泼溅模型，提出在运动轨迹上嵌入水印信号并利用视频-文本潜空间解码器恢复水印，为动态场景资产版权保护提供可复用技术。
原文依据 Embedding invisible and temporally consistent watermarks into dynamic 4D Gaussian Splatting (4DGS) models poses unique challenges
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论由于高斯在时空上的连续变形以及多样的运动动态，将不可见且时序一致的水印嵌入动态4D高斯泼溅（4DGS）模型面临独特挑战。现有的3DGS水印方法直接微调高斯泼溅内的参数，在扩展到4D设置时无法保持几何保真度和时序一致性。针对这一情况，我们提出Mark4D，一种时序一致的水印技术，为4DGS实现鲁棒、不可感知且运动感知的水印嵌入。Mark4D包括：1）在视频-文本潜空间中进行水印恢复的解码器，以抵御像素级失真；2）轨迹对齐偏移，沿高斯运动路径嵌入水印信号以保持几何；3）运动自适应损失加权策略，平衡不同运动强度帧之间的监督。在合成和真实动态场景数据集上的大量实验证明了我们方法的有效性，为动态4D场景资产的安全可靠保护奠定了基础。
英文原文摘要 1138 字符
Embedding invisible and temporally consistent watermarks into dynamic 4D Gaussian Splatting (4DGS) models poses unique challenges due to continuous spatio-temporal deformation of Gaussians and diverse motion dynamics. Existing 3DGS watermarking methods, which directly fine-tune parameters within Gaussian splats, fail to preserve geometric fidelity and temporal coherence when extended to 4D settings. In this regime, we propose Mark4D, a temporally consistent watermarking technique that achieves robust, imperceptible, and motion-aware watermark embedding for 4DGS. Mark4D comprises 1) a decoder for watermark recovery in the latent video-text space for robustness against pixel-level distortions, 2) trajectory-aligned offsets that embed watermark signals along Gaussian motion paths to preserve geometry, and 3) a motion-adaptive loss weighting strategy that balances supervision across frames with varying motion intensities. Extensive experiments on synthetic and real-world dynamic scene datasets demonstrate the effectiveness of our method, establishing a foundation for secure and reliable protection of dynamic 4D scene assets.