OSI: 一步反向在提取扩散水印中表现优异
OSI: One-step Inversion Excels in Extracting Diffusion Watermarks
AI总结：
OSI通过一步反向高效提取高斯阴影水印，速度快20倍，精度更高，承载能力翻倍。
摘要：
水印技术是保护扩散生成图像来源和版权的重要机制。无需训练的方法，例如高斯阴影，通过在扩散模型的初始噪声中嵌入水印，对生成图像的质量影响极小。然而，提取此类水印通常需要多步扩散反向以获得精确的初始噪声，这计算成本高且耗时。为了解决这一问题，我们提出了一步反向（OSI），一种显著更快且更准确的提取高斯阴影风格水印的方法。OSI将水印提取重新表述为一个可学习的符号分类问题，从而消除了对初始噪声精确回归的需要。然后，我们从扩散主干网络初始化OSI模型，并在合成噪声-图像对上进行微调，以符号分类为目标。通过这种方式，OSI模型能够在仅一步中高效完成水印提取。我们的OSI在多步扩散反向方法上表现显著优于：它快20倍，提取精度更高，并且水印承载能力翻倍。在广泛的调度器、扩散主干网络和密码学方案上的广泛实验一致显示了改进，证明了我们的OSI框架的通用性。
英文摘要：
Watermarking is an important mechanism for provenance and copyright protection of diffusion-generated images. Training-free methods, exemplified by Gaussian Shading, embed watermarks into the initial noise of diffusion models with negligible impact on the quality of generated images. However, extracting this type of watermark typically requires multi-step diffusion inversion to obtain precise initial noise, which is computationally expensive and time-consuming. To address this issue, we propose One-step Inversion (OSI), a significantly faster and more accurate method for extracting Gaussian Shading style watermarks. OSI reformulates watermark extraction as a learnable sign classification problem, which eliminates the need for precise regression of the initial noise. Then, we initialize the OSI model from the diffusion backbone and finetune it on synthesized noise-image pairs with a sign classification objective. In this manner, the OSI model is able to accomplish the watermark extraction efficiently in only one step. Our OSI substantially outperforms the multi-step diffusion inversion method: it is 20x faster, achieves higher extraction accuracy, and doubles the watermark payload capacity. Extensive experiments across diverse schedulers, diffusion backbones, and cryptographic schemes consistently show improvements, demonstrating the generality of our OSI framework.
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。
