扩散模型中的水印：基于耦合变换精确扩散反转（EDICT）的高斯着色法
Watermarking in Diffusion Model: Gaussian Shading with Exact Diffusion Inversion via Coupled Transformations (EDICT)
AI总结：
本研究将EDICT框架与高斯着色水印技术结合，通过双隐变量往复交替的去噪加噪方案实现精确反转，在标准数据集上实现了统计显著的水印恢复保真度提升，为扩散模型水印研究开辟新方向。
摘要：
本文提出一种新方法，通过整合基于耦合变换的精确扩散反转（Exact Diffusion Inversion via Coupled Transformations，EDICT）框架，来提升主流水印技术高斯着色（Gaussian Shading）的性能。传统高斯着色方法在噪声隐空间中嵌入水印，随后通过迭代去噪生成图像，再通过加噪恢复水印，但其反转过程并不精确，可能导致水印失真。我们提出利用EDICT推导精确逆映射的能力来优化这一过程。我们的方法包括复制注入水印的噪声隐变量，并借助EDICT在两个隐变量之间采用往复交替的去噪与加噪方案。这使得图像和嵌入水印的重建都更为精确。在标准数据集上的实证评估表明，我们的集成方法在水印恢复保真度上实现了微小但具有统计显著性的提升。这些结果凸显了EDICT通过提供更精确、更鲁棒的反转机制，来增强现有基于扩散的水印技术的潜力。据我们所知，这是首个探索EDICT与高斯着色在数字水印领域协同作用的工作，为鲁棒高保真水印嵌入与提取的研究开辟了新方向。
英文摘要：
This paper introduces a novel approach to enhance the performance of Gaussian Shading, a prevalent watermarking technique, by integrating the Exact Diffusion Inversion via Coupled Transformations (EDICT) framework. While Gaussian Shading traditionally embeds watermarks in a noise latent space, followed by iterative denoising for image generation and noise addition for watermark recovery, its inversion process is not exact, leading to potential watermark distortion. We propose to leverage EDICT's ability to derive exact inverse mappings to refine this process. Our method involves duplicating the watermark-infused noisy latent and employing a reciprocal, alternating denoising and noising scheme between the two latents, facilitated by EDICT. This allows for a more precise reconstruction of both the image and the embedded watermark. Empirical evaluation on standard datasets demonstrates that our integrated approach yields a slight, yet statistically significant improvement in watermark recovery fidelity. These results highlight the potential of EDICT to enhance existing diffusion-based watermarking techniques by providing a more accurate and robust inversion mechanism. To the best of our knowledge, this is the first work to explore the synergy between EDICT and Gaussian Shading for digital watermarking, opening new avenues for research in robust and high-fidelity watermark embedding and extraction.
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。
