arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2509.00757cs.CV

MarkSplatter:基于Splatter Image结构的3D高斯溅射模型通用水印方法

MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure

Department of Computer Science, Hong Kong Baptist University(香港 Baptist 大学计算机科学系)

Xiufeng Huang, Ziyuan Luo, Qi Song, Ruofei Wang, Renjie Wan

AI总结:

针对现有3DGS水印需为每条消息高成本微调的问题,提出首个通用3DGS水印框架MarkSplatter,通过GaussianBridge转换格式、不确定性感知热图保不可感知性、密集分割提取保鲁棒性,单次前向传播即可完成水印嵌入。

摘要:

3D高斯溅射(3D Gaussian Splatting, 3DGS)的日益普及,使得对有效版权保护的需求愈发迫切。当前的3DGS水印方法需要为每条预定义消息执行计算成本高昂的微调流程。我们提出了首个通用水印框架,仅需单次前向传播即可高效保护基于Splatter Image的3DGS模型。我们引入GaussianBridge模块,将非结构化3D高斯转换为Splatter Image格式,从而支持直接通过神经处理嵌入任意消息。为保证水印的不可感知性,我们设计了高斯-不确定性-感知热图预测策略,以保留视觉质量。为实现鲁棒的消息恢复,我们开发了基于密集分割的提取机制,即便水印对象在渲染视图中仅占极小区域,仍能保持可靠的提取效果。项目主页:https://kevinhuangxf.github.io/marksplatter

英文摘要:

The growing popularity of 3D Gaussian Splatting (3DGS) has intensified the need for effective copyright protection. Current 3DGS watermarking methods rely on computationally expensive fine-tuning procedures for each predefined message. We propose the first generalizable watermarking framework that enables efficient protection of Splatter Image-based 3DGS models through a single forward pass. We introduce GaussianBridge that transforms unstructured 3D Gaussians into Splatter Image format, enabling direct neural processing for arbitrary message embedding. To ensure imperceptibility, we design a Gaussian-Uncertainty-Perceptual heatmap prediction strategy for preserving visual quality. For robust message recovery, we develop a dense segmentation-based extraction mechanism that maintains reliable extraction even when watermarked objects occupy minimal regions in rendered views. Project page: https://kevinhuangxf.github.io/marksplatter.

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。

↑