63 datasets found

Formats: JSON

Filter Results

  • Kodak lossless true color image suite

    The Kodak lossless true color image suite is a collection of 24 images.

  • RealLR200

    Real-world image super-resolution dataset

  • Real-ISR

    Real-world image super-resolution dataset

  • Real-ESRGAN+

    Real-ESRGAN+: Real-World Blind Super-Resolution with Sharpened Ground-Truths

  • Flickr2K dataset

    The Flickr2K dataset is a low-resolution image dataset used for image super-resolution tasks.

  • DIV2K+Flickr2K dataset

    Dataset for single image super-resolution

  • Photorealistic text-to-image diffusion models with deep language understanding

    The authors present a photorealistic text-to-image diffusion model with deep language understanding.

  • Flickr1024

    Stereo image super-resolution aims to improve the quality of high-resolution stereo image pairs by exploiting complementary information across views.

  • DIV2K, OST, FFHQ, and CeleA-HQ Datasets

    The dataset used in the paper is not explicitly described, but it is mentioned that the authors used DIV2K, OST, FFHQ, and CeleA-HQ datasets.

  • Middlebury

    The Middlebury dataset is a benchmark for stereo vision and 3D reconstruction.

  • Real-ESRGAN

    Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

  • DIV8K

    The dataset used for training and testing the proposed super-resolution model.

  • Cai et al. RealSR dataset

    Real-world super-resolution (RealSR) dataset by capturing the LR-HR image pairs on the same scene with different focal lengths of a digital camera.

  • Manga109

    The dataset used in the paper is a synthetic dataset for blind super-resolution, consisting of low-resolution images and their corresponding blur kernels.

  • Urban100

    The dataset used in the paper is a synthetic dataset for blind super-resolution, consisting of low-resolution images and their corresponding blur kernels.

  • B100

    The dataset used for training and testing the proposed Incremental Residual Learning (IRL) framework.

  • Set14

    Implicit neural representation, which expresses an image as a continuous function rather than a discrete grid form, is widely used for image processing. The dataset used in this...

  • Set5

    The dataset used in the paper is a synthetic dataset for blind super-resolution, consisting of low-resolution images and their corresponding blur kernels.

  • DRealSR

    Real-world super-resolution (RealSR) dataset by adjusting the focal length of a digital camera, and introducing the Laplacian pyramid based kernel prediction network (LP-KPN) to...

  • RealSR

    The RealSR dataset contains 595 pairs of HR and LR images captured by adjusting focal length through Canon and Nikon DSLR cameras.