AI 中文总结
针对扩散模型语义水印提取，提出区域感知反演网络，通过分解端点恢复实现高效一步提取，避免迭代反演，计算成本低于现有方法。
AI 中文摘要
扩散模型的语义水印在保持感知质量的同时，将所有权信息嵌入生成过程，但高斯阴影提取传统上需要多步扩散反演来恢复初始噪声。最近的一步法表明，这一成本可以大幅降低。我们通过扩展流匹配和条件回归来研究这一问题。关键观察是，在高信噪比图像端点附近，恢复由扩展流匹配在高信噪比区域的第一步输出给出的有用噪声统计量，远比重建完整反演轨迹简单，且高斯阴影仅要求恢复的潜变量保持在正确的 watermark 决策区域内。基于这一观察，我们提出了一种轻量级、无需提示的提取器，将端点恢复分解为图像样锚点和噪声导向残差，这增强了模型利用 GPU 并行计算的能力。所提方法避免了迭代反演和重复评估扩散规模 U-Net，提供了一种高效的一步提取流程，并具有简洁的理论解释。提取噪声的计算成本低于 OSI 和 FARI。GitHub 仓库位于：此 https URL
英文摘要
Semantic watermarks for diffusion models embed ownership information into the generative process while preserving perceptual quality, but Gaussian-Shading extraction conventionally requires multi-step diffusion inversion to recover the initial noise. Recent one-step methods show that this cost can be reduced substantially. We study this problem through extended flow matching and conditional regression. The key observation is that, near the high-SNR image endpoint, recovering a useful noise statistic given by the first-step output of the extended flow matching in the high-SNR regime is much simpler than reconstructing the full inverse trajectory, and Gaussian Shading only requires the recovered latent to remain in the correct watermark decision region. Based on this observation, we propose a lightweight, prompt-free extractor that decomposes endpoint recovery into an image-like anchor and a noise-oriented residual, which increases the capability of the model to utilize GPU parallel computation. The resulting method avoids iterative inversion and repeated evaluation of a diffusion-scale U-Net, providing an efficient one-step extraction pipeline with a concise theoretical interpretation. The computational cost of extracting noise is lower than that of both OSI and FARI. The github repo is there: https://github.com/TheLovesOfLadyPurple/RAIN-lightweight-NN-for-one-step-semantic-watermark-extraction
