Exciting news! Gradient has launched a FREE GPU plan. Read More
Project Details

Image Super-Resolution

Make low resolution images high resolution using ESPCN

The Gradient Team


ESPCN consists of convolutional layers for feature extraction, followed by sub-pixel convolution for upsampling. We'll use the DIV2K dataset for training.

For a deeper explanation of the concepts covered in this notebook, check out Image Super-Resolution: A Comprehensive Review on the blog.