Restoring Deteriorated Images using Deep Learning Techniques: Region Filling, Median Filter

Abstract

Image restoration is a technique for recovering images from corrupted images that have blur and noise, lowering the image's quality. Motion blur, low resolution, moisture in the atmosphere, and other factors can all contribute to image noise. For noise removal, there are a variety of restoration techniques and a spatial domain filter. To eliminate blur and scratches in deteriorated photographs, an image restoration method has been developed. Deep learning has gained popularity as a method for image restoration during the last few years. Denoising and other image restoration operations are necessary steps in many image processing applications. Image fusion using the stacked median operator, low resolution detail improvement using guided super sampling, and repeated visual consistency assessment and refining are the three processes in the restoration process. Two VAEs (Variational Autoencoders) are trained in this model to translate old and clean pictures into two latent spaces, respectively. This is due to the fact that they are all using supervised learning, which is a difficulty created by the domain gap between the original image and the ones synthesized for training. The suggested project offers a cost-effective solution that can deal with noise, picture rotations, and occlusions.