Train a Very-Deep Super-Resolution (VDSR) neural network, then use a VDSR network to estimate a high-resolution image from a single low-resolution image.
Remove Gaussian noise from an RGB image. Split the image into separate color channels, then denoise each channel using a pretrained denoising neural network, DnCNN.
Train a denoising convolutional neural network (DnCNN), then use the network to reduce JPEG compression artifacts in an image.
Train a multiscale context aggregation network (CAN) that is used to approximate an image filtering operation.