Images

Set5

Introduced in Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding2011

About this Dataset

The Set5 dataset is a dataset consisting of 5 images (“baby”, “bird”, “butterfly”, “head”, “woman”) commonly used for testing performance of Image Super-Resolution models. Image Source: http://people.rennes.inria.fr/Aline.Roumy/results/SR_BMVC12.html

Source: Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding

Dataset Variants

Set5 - 4x upscalingSet5-2xSet5 - 3x upscalingSet5 - 2x upscalingSet5 - 8x upscalingSet5

Papers1

Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding

The neighbor embedding SR algorithm so designed is shown to give good visual results, comparable to other state-of-the-art methods, while presenting an appreciable reduction of the computational time.

Dataset Loaders

EDIT

🔥

eugenesiow/super-image-data

pytorch

Tasks

EDIT

Image Super-Resolution Blind Super-Resolution Image Rescaling Compressive Sensing

Similar Datasets