The DIV2K dataset is one of the most popular datasets used for image super-resolution, which is collected for NTIRE2017 and NTIRE2018 Super-Resolution Challenges. The dataset is composed of 800 images for training, 100 images for validation, and 100 images for testing. Each image has a 2K resolution. The official page of this dataset is here. This dataset contains the original high resolution images, bicubic downscaled 2x and 4x images. It contains the train and validation dataset. All the credits and right belongs to the original owners, I have uploaded here to conveniently create notebook and so that other can create notebooks for super resolution.

yangtao9009/DIV2K dataset hosted on Hugging Face and contributed by the HF Datasets community

DIV2K

## Overview

DIV2K is a dataset for object detection tasks - it contains DIV2K annotations for 800 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Dataset

This dataset was created by Bảo Ngô

Contents

The dataset used in the paper for neural image compression.

Dataset

This dataset was created by Francesco Pignatelli

Contents

Dataset

This dataset was created by Rajveer Yadav

Contents

Dataset

This dataset was created by Tharusha Pathirana

Contents

Dataset

This dataset was created by Manas Sambare

Contents

DF2K+OST Dataset

The DF2K+OST dataset is a combination of three popular datasets used for training and benchmarking image super-resolution models:

DIV2K: A high-quality dataset for image super-resolution. Flickr2K: A dataset with diverse images from Flickr, complementing DIV2K. OST (OutdoorSceneTraining): A dataset containing high-quality outdoor images.

  Overview

The DF2K+OST dataset provides high-resolution images and their corresponding low-resolution versions for… See the full description on the dataset page: https://huggingface.co/datasets/ItzLoghotXD/DF2K_OST.

Dataset

This dataset was created by dntai2

Released under Apache 2.0

Contents

Dataset

This dataset was created by Aritra Roy Gosthipaty

Contents

The color images in the DIV2K are converted to grayscale images before generating HR patches and LR patches, as the majority of real neutron images are grayscale images with unknown blur. Bicubic interpolation is then used to create the LR patches. Finally, the LR patches are blurred to simulate the neutron image using the Gaussian blur of random kernel size or the average blur of random kernel size.

Dataset

This dataset was created by BNULChang

Contents

Dataset

This dataset was created by JIN

Contents

Dataset

This dataset was created by Yash Bansal

Contents

Dataset

This dataset was created by guilherme santana

Contents

Dataset

This dataset was created by 颀周

Contents

Dataset

This dataset was created by 颀周

Contents

Dataset

This dataset was created by aaron-ta

Contents