用深度水印技术提升图像同步鲁棒性，对抗裁剪旋转等几何变换。
Geometric Image Synchronization with Deep Watermarking
- 设计端到端训练的嵌入与提取网络，隐式嵌入几何变换信息。
- 在多种几何和度量变换下实现高精度图像同步，误差极低。
- 可兼容现有水印方法，显著增强其对几何攻击的防御能力。
同步任务旨在估计并逆向几何变换（如裁剪、旋转）对图像的影响。本文提出 SyncSeal，一种专用于增强图像同步鲁棒性的深度水印方法，可叠加于现有水印技术之上，提升其对几何变换的抗性。该方法依赖一个嵌入网络，以不可察觉的方式修改图像，并配合一个提取网络，预测图像所受几何变换参数。两个网络通过联合优化预测误差与感知质量（引入判别器）进行端到端训练。我们在多种几何及度量变换下验证了该方法的有效性，证明其能精确还原图像变换。此外，我们还展示了该同步机制可有效提升现有水印方案对几何攻击的抵抗力，使其在以往易受攻击的场景中依然稳健。
原文摘要 · Abstract (English)
Synchronization is the task of estimating and inverting geometric transformations (e.g., crop, rotation) applied to an image. This work introduces SyncSeal, a bespoke watermarking method for robust image synchronization, which can be applied on top of existing watermarking methods to enhance their robustness against geometric transformations. It relies on an embedder network that imperceptibly alters images and an extractor network that predicts the geometric transformation to which the image was subjected. Both networks are end-to-end trained to minimize the error between the predicted and ground-truth parameters of the transformation, combined with a discriminator to maintain high perceptual quality. We experimentally validate our method on a wide variety of geometric and valuemetric transformations, demonstrating its effectiveness in accurately synchronizing images. We further show that our synchronization can effectively upgrade existing watermarking methods to withstand geometric transformations to which they were previously vulnerable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。