Deep Denoising Improved Super-Resolution Framework based on Convolutional Neural Network

The best method currently being employed in computer vision is super-resolution. This method is used to create high-resolution images from a single low-resolution image with the goals of boosting the frequency component, retrieving lost data, and removing downsampling and noises produced during the image capture process. The fundamental objective of the super-resolution technique is to create a high resolution image by combining non-repetition information inside one or more low-resolution frames. Numerous methods have been put forth in the past where numerous photos are used as low resolution images of the same scene with various transformations. Multi-image super resolution is the term used for this. By using deep learning method high resolution image can be reconstructed very easily. In this research, a deep neural network has been proposed to reconstruct the high resolution image from low resolution image very effectively. Proposed method is name as DDSR i.e. Deep Denoising Super Resolution.