Visual Watermark Removal Based on Deep Learning
This work addresses the need for clean, unobstructed images in social media and digital content, but it is incremental as it builds upon existing U-structure methods with specific architectural improvements.
The paper tackles the problem of removing visual watermarks from images by proposing an end-to-end deep neural network called AdvancedUnet, which uses RSU modules and deep-supervised hybrid loss to achieve effective removal, as demonstrated in comparison experiments.
In recent years as the internet age continues to grow, sharing images on social media has become a common occurrence. In certain cases, watermarks are used as protection for the ownership of the image, however, in more cases, one may wish to remove these watermark images to get the original image without obscuring. In this work, we proposed a deep learning method based technique for visual watermark removal. Inspired by the strong image translation performance of the U-structure, an end-to-end deep neural network model named AdvancedUnet is proposed to extract and remove the visual watermark simultaneously. On the other hand, we embed some effective RSU module instead of the common residual block used in UNet, which increases the depth of the whole architecture without significantly increasing the computational cost. The deep-supervised hybrid loss guides the network to learn the transformation between the input image and the ground truth in a multi-scale and three-level hierarchy. Comparison experiments demonstrate the effectiveness of our method.