GuardSplat：面向3D Gaussian Splatting的高效鲁棒水印
GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
AI总结：
针对3DGS资产版权保护难题，本文提出GuardSplat水印框架，通过CLIP引导解码、SH感知嵌入和抗失真提取实现高效、安全、鲁棒的水印。
摘要：
3D Gaussian Splatting（3DGS）近来已为各类应用生成了令人印象深刻的3D资产。然而，从安全性、容量、不可见性和训练效率等方面考虑，3DGS资产的版权尚未得到良好保护，因为现有水印方法并不适配其渲染流水线。本文提出GuardSplat，这是一个新颖且高效的3DGS资产水印框架。具体而言：1）我们提出一种CLIP引导的流水线，以最低成本优化消息解码器。其核心目标是利用CLIP的对齐能力和丰富表示实现高精度提取，展现出卓越的容量与效率。2）我们为3DGS定制了球谐感知（Spherical-Harmonic-aware，SH-aware）消息嵌入模块，在保留原始3D结构的同时，将消息无缝嵌入每个3D Gaussian的SH特征中。这使得在以最小保真度代价为3DGS资产加水印的同时，可防止恶意用户从模型文件中移除水印，满足不可见性与安全性需求。3）我们提出抗失真消息提取模块，以增强对多种失真的鲁棒性。实验表明，GuardSplat优于现有最先进方法，并实现了快速优化速度。项目主页位于https://narcissusex.github.io/GuardSplat，代码位于https://github.com/NarcissusEx/GuardSplat。
英文摘要：
3D Gaussian Splatting (3DGS) has recently created impressive 3D assets for various applications. However, considering security, capacity, invisibility, and training efficiency, the copyright of 3DGS assets is not well protected as existing watermarking methods are unsuited for its rendering pipeline. In this paper, we propose GuardSplat, an innovative and efficient framework for watermarking 3DGS assets. Specifically, 1) We propose a CLIP-guided pipeline for optimizing the message decoder with minimal costs. The key objective is to achieve high-accuracy extraction by leveraging CLIP's aligning capability and rich representations, demonstrating exceptional capacity and efficiency. 2) We tailor a Spherical-Harmonic-aware (SH-aware) Message Embedding module for 3DGS, seamlessly embedding messages into the SH features of each 3D Gaussian while preserving the original 3D structure. This enables watermarking 3DGS assets with minimal fidelity trade-offs and prevents malicious users from removing the watermarks from the model files, meeting the demands for invisibility and security. 3) We present an Anti-distortion Message Extraction module to improve robustness against various distortions. Experiments demonstrate that GuardSplat outperforms state-of-the-art and achieves fast optimization speed. Project page is at https://narcissusex.github.io/GuardSplat, and Code is at https://github.com/NarcissusEx/GuardSplat.
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。
