路标水印：视觉水印共存的联合优化方法

AI 摘要

本文提出了一种名为“Signpost Watermarking”的方法，通过联合优化训练不可感知的视觉水印，使其能与独立部署的其他水印系统共存。作者首先实证发现视频水印也具备图像水印中的共存特性，然后引入解码器感知的训练目标，在保持水印鲁棒性和视觉质量的同时，显著提升共存性能。该方法支持分层溯源信号，为内容真实性和版权保护提供了实用路径。

正文节选

Signpost Watermarking: Joint Optimization for Visual Watermark Coexistence Abstract We present a method for training imperceptible visual watermarks to coexist with other such watermarks. Recent work has shown that independently trained image watermarking models can coexist with surprisingly limited interference, enabling watermark ensembling. However, this coexistence is a serendipitous property rather than an explicit optimization objective, leaving interference uncontrolled and potentially re

发布时间：2026-08-12 12:00

抓取时间：2026-08-12 12:42

来源机构：arXiv