Abstract
Imperceptible digital watermarking is important in copyright protection, misinformation prevention, and responsible generative AI. We propose TrustMark - a watermarking method that leverages a spatio-spectral loss function and a 1 × 1 convolution layer to enhance encoding quality. TrustMark is robust against both in-place and out-of-place perturbations while maintaining image quality above 43 dB. Additionally, we propose ReMark, a watermark removal method designed for re-watermarking, along with a simple yet effective algorithm that enables both TrustMark and ReMark to operate across arbitrary resolutions. Our methods achieve state-of-art performance on 3 benchmarks 1 1 Models and code are released under MIT license at https://github.com/adobe/trustmark..