Robust Invisible Video Watermarking with Attention
This addresses the problem of asserting ownership over video content for media producers, representing an incremental improvement in deep learning-based watermarking.
The paper tackled robust invisible video watermarking by introducing RivaGAN, an architecture with an attention-based embedding mechanism and adversarial networks, achieving state-of-the-art results with minimal visual distortion and robustness against common video processing operations.
The goal of video watermarking is to embed a message within a video file in a way such that it minimally impacts the viewing experience but can be recovered even if the video is redistributed and modified, allowing media producers to assert ownership over their content. This paper presents RivaGAN, a novel architecture for robust video watermarking which features a custom attention-based mechanism for embedding arbitrary data as well as two independent adversarial networks which critique the video quality and optimize for robustness. Using this technique, we are able to achieve state-of-the-art results in deep learning-based video watermarking and produce watermarked videos which have minimal visual distortion and are robust against common video processing operations.