Image inpainting for corrupted images by using the semi-super resolution GAN
This work addresses image enhancement for corrupted images, but it appears incremental as it builds on existing GAN and SRGAN methods.
The paper tackled the problem of restoring images with varying levels of corruption by introducing a Generative Adversarial Network (GAN) and a Semi-Super-Resolution GAN variant, achieving optimal accuracy and high-quality image generation through training on diverse datasets.
Image inpainting is a valuable technique for enhancing images that have been corrupted. The primary challenge in this research revolves around the extent of corruption in the input image that the deep learning model must restore. To address this challenge, we introduce a Generative Adversarial Network (GAN) for learning and replicating the missing pixels. Additionally, we have developed a distinct variant of the Super-Resolution GAN (SRGAN), which we refer to as the Semi-SRGAN (SSRGAN). Furthermore, we leveraged three diverse datasets to assess the robustness and accuracy of our proposed model. Our training process involves varying levels of pixel corruption to attain optimal accuracy and generate high-quality images.