A self-supervised CNN for image watermark removal

arXiv:2403.05807v1 Announce Type: new
Abstract: Popular convolutional neural networks mainly use paired images in a supervised way for image watermark removal. However, watermarked images do not have reference images in the real world, which results in poor robustness of image watermark removal techniques. In this paper, we propose a self-supervised convolutional neural network (CNN) in image watermark removal (SWCNN). SWCNN uses a self-supervised way to construct reference watermarked images rather than given paired training samples, according to watermark distribution. A …

abstract arxiv cnn convolutional neural network convolutional neural networks cs.cv eess.iv however image images network networks neural network neural networks paper popular reference results robustness type watermark world