Watermarks are commonly used to protect the ownership and copyright of digital media. However, there are legitimate scenarios where watermark removal is necessary. Recent advancements in deep learning have led to the development of sophisticated techniques for both detecting and removing watermarks.this research provides a summary of methods for detecting and removing Regenerative AdversarialNetworks (GANs) are one noteworthy method. It is possible to train GANs to recognize watermark patterns and produce unwatermarked versions of watermarked content. One such method, which uses GANs to find and remove watermarks in deep neural networks (DNNs), has been demonstrated to be successful even when it comes to DNN watermarks that are based on backdoors.Another method makes use of deep neural networks' U-structure, which is highly effective in translating images. A comprehensive model like the AdvancedUnet has been developed to concurrently extract and remove visual watermarks. This model uses a deep-supervised hybrid loss to direct the network in learning the transformation between the watermarked input and the clean ground truth. It also integrates efficient modules to extend the architecture's depth without appreciably increasing computingcosts.