Geometric Image Synchronization with Deep Watermarking
This work addresses the problem of geometric image synchronization for applications in watermarking and image processing, representing an incremental improvement by building on existing methods.
The paper tackles the problem of estimating and inverting geometric transformations in images by introducing SyncSeal, a deep watermarking method that enhances robustness against such transformations. It demonstrates effectiveness in accurately synchronizing images and upgrading existing watermarking methods to withstand previously vulnerable geometric attacks.
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.