The dataset has been collected from Unsplash.com (https://unsplash.com/data). It provides the world's largest open library dataset for free. The Unsplash Dataset is created by 250,000+ contributing photographers and billions of searches across thousands of applications, uses, and contexts.

The dataset has been preprocessed to generate data for the problem of Image Super Resolution. The high resolution images have been depixelated at three different levels 2,4,6

Example:-

• 234_2.jpg: image has been depixelated at 1/2 the size of the original image
• 15_4.jpg: image has been depixelated at 1/4 the size of the original image
• 190_6.jpg: image has been depixelated at 1/6 the size of the original image