A self-supervised CNN for image watermark removal
This addresses the robustness issue in image watermark removal for real-world applications where reference images are unavailable, though it appears incremental as it builds on existing CNN architectures.
The paper tackles the problem of image watermark removal by proposing a self-supervised CNN that constructs reference watermarked images based on watermark distribution, eliminating the need for paired training samples. Experimental results show it outperforms popular CNNs in this task.
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 heterogeneous U-Net architecture is used to extract more complementary structural information via simple components for image watermark removal. Taking into account texture information, a mixed loss is exploited to improve visual effects of image watermark removal. Besides, a watermark dataset is conducted. Experimental results show that the proposed SWCNN is superior to popular CNNs in image watermark removal.