GS-Marker：面向3D高斯泼溅的通用鲁棒水印技术
GS-Marker: Generalizable and Robust Watermarking for 3D Gaussian Splatting
AI总结：
针对3D模型水印泛化性差、效率低的问题，提出面向3D高斯泼溅的GS-Marker水印框架，通过自适应标记控制机制提升训练效果，在解码精度、保真度和计算效率上均优于现有逐场景优化方法。
摘要：
在生成式AI时代，3D模型的安全保护需求日益迫切。尽管基于编解码框架的不可见水印技术在2D图像领域已十分成熟，但针对3D场景的通用鲁棒水印解决方案仍有待突破。核心难点在于3D编码器与2D解码器之间存在渲染器，会阻断直接的梯度流动，导致训练过程复杂化。现有3D水印方法通常依赖逐场景的迭代优化，存在时间效率低、泛化性有限的问题。\n本文针对3D高斯泼溅（3D Gaussian Splatting，3DGS）——一种应用广泛但水印研究尚不充分的3D表示方法——提出了一种单次前向的水印生成方法。研究明确了两大核心挑战：一是实现跨多样3D模型的有效泛化训练，二是即使存在失真，也能从自由视角渲染结果中可靠提取水印。所提框架GS-Marker包含用于嵌入信息的3D编码器、用于提升各类失真鲁棒性的失真层，以及用于从渲染图中提取水印的2D解码器。其核心创新为自适应标记控制机制，可对初始优化后的3DGS进行自适应扰动，从而逃离局部最优，提升训练稳定性与收敛速度。\n大量实验表明，GS-Marker在解码准确率与模型保真度上均优于逐场景训练方法，同时大幅缩短了计算时间。
英文摘要：
In the Generative AI era, safeguarding 3D models has become increasingly urgent. While invisible watermarking is well-established for 2D images with encoder-decoder frameworks, generalizable and robust solutions for 3D remain elusive. The main difficulty arises from the renderer between the 3D encoder and 2D decoder, which disrupts direct gradient flow and complicates training. Existing 3D methods typically rely on per-scene iterative optimization, resulting in time inefficiency and limited generalization. In this work, we propose a single-pass watermarking approach for 3D Gaussian Splatting (3DGS), a well-known yet underexplored representation for watermarking. We identify two major challenges: (1) ensuring effective training generalized across diverse 3D models, and (2) reliably extracting watermarks from free-view renderings, even under distortions. Our framework, named GS-Marker, incorporates a 3D encoder to embed messages, distortion layers to enhance resilience against various distortions, and a 2D decoder to extract watermarks from renderings. A key innovation is the Adaptive Marker Control mechanism that adaptively perturbs the initially optimized 3DGS, escaping local minima and improving both training stability and convergence. Extensive experiments show that GS-Marker outperforms per-scene training approaches in terms of decoding accuracy and model fidelity, while also significantly reducing computation time.
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。
