路标水印：面向视觉水印共存的联合优化
Signpost Watermarking: Joint Optimization for Visual Watermark Coexistence
查看机构详情
- Adobe Research（奥多比研究院）
- University of Surrey（萨里大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究提出路标水印的联合优化方法，使视觉水印可与其他水印共存，提升解码鲁棒性，支持内容真实性与版权的分层溯源信号。
中文摘要 AI 辅助
我们提出一种训练不可感知视觉水印的方法，使其可与其他同类水印共存。近期研究表明，独立训练的图像水印模型可在干扰极小的情况下共存，实现水印集成。但这种共存是偶然特性，而非显式优化目标，导致干扰不受控，可能降低解码鲁棒性或视觉质量。我们首先通过实验证明，相同的共存特性可扩展至视频水印。随后，我们证明图像和视频水印均可采用感知解码器的目标函数进行训练，以提升共存性。我们的结果表明，存在一条实用路径可实现路标水印，用于指示独立部署的溯源水印系统的存在，支持用于内容真实性和版权的分层溯源信号。
英文摘要
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 reducing decoding robustness or visual quality. We first show empirically that the same coexistence property extends to video watermarking. We then show that both image and video watermarks can be trained with a decoder-aware objective to improve coexistence. Our results suggest a practical path to signpost watermarks that indicate the presence of independently deployed provenance watermarking systems, supporting layered provenance signaling for content authenticity and rights.
