LECA: A learned approach for efficient cover-agnostic watermarking

In this work, we present an efficient multi-bit deep image watermarking method that is cover-agnostic yet also robust to geometric distortions such as translation and scaling well other JPEG compression noise. Our design consists of a light-weight watermark encoder jointly trained with neural network based decoder. Such allows us retain the efficiency while fully utilizing power network. Moreover, independent content, allowing users pre-generate watermarks for further efficiency. To offer robustness towards transformations, introduced learned model predicting scale offset watermarked images. our making generated universally applicable different cover Experiments show outperforms comparably methods by large margin.