DVMark: A Deep Multiscale Framework for Video Watermarking
This addresses the need for robust video watermarking against diverse distortions, though it is incremental as it builds on deep learning approaches.
The authors tackled the problem of robust video watermarking by proposing a deep multiscale framework that distributes watermarks across spatial-temporal scales, outperforming traditional and deep image methods by a large margin on various distortions.
Video watermarking embeds a message into a cover video in an imperceptible manner, which can be retrieved even if the video undergoes certain modifications or distortions. Traditional watermarking methods are often manually designed for particular types of distortions and thus cannot simultaneously handle a broad spectrum of distortions. To this end, we propose a robust deep learning-based solution for video watermarking that is end-to-end trainable. Our model consists of a novel multiscale design where the watermarks are distributed across multiple spatial-temporal scales. It gains robustness against various distortions through a differentiable distortion layer, whereas non-differentiable distortions, such as popular video compression standards, are modeled by a differentiable proxy. Extensive evaluations on a wide variety of distortions show that our method outperforms traditional video watermarking methods as well as deep image watermarking models by a large margin. We further demonstrate the practicality of our method on a realistic video-editing application.