22 datasets found

Simultaneous enhancement and super-resolution of underwater imagery for improved visual perception.

Single image super-resolution (SISR) reconstruction for magnetic resonance imaging (MRI) has generated significant interest because of its potential to not only speed up imaging...

The NTIRE2018 dataset is acquired by a Specim PS Kappa DX4 hyperspectral camera.

The NUS dataset is captured by a Specim’s PFDCL-65-V10E spectral camera.

The CAVE dataset is comprised of 32 scenes of a wide range of materials and objects, such as skin, fruits, drinks, feathers, paintings, etc.

Hyperspectral image super-resolution (HSI SR) task is critical and meaningful to enhance the image quality to better serve the subsequent high-level computer vision tasks.

Video super-resolution (VSR) is the technique of increasing the nominal resolution of image/video content accompanied with quality improvement.

The dataset used for training the Pixel2Style2Pixel encoder consists of degraded copies of high-resolution images.

The dataset used for super-resolution is DIV2K, CelebA, and Set5.

The Vid4 dataset is a video super-resolution dataset, which consists of 4 videos of resolution 640 x 480.

The REDS dataset is a video super-resolution dataset, which consists of 240 videos of resolution 720 x 1280 captured by GoPro. Each video consists of 100 HR frames.

Generative Adversarial Networks (GANs) consist of two networks: a generator G(z) and a discriminator D(x). The discriminator is trying to distinguish real objects from objects...

High-resolution diffusion-weighted images (DWIs) from low-resolution DWIs using a deep learning-based super-resolution method entitled “SRDTI” to synthesize high-resolution...

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

Recent years have witnessed the dramatic growth of Internet video traffic, where the video bitstreams are often compressed and delivered in low quality to fit the streamer’s...

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used ImageNet and several famous super-resolution image datasets.

The dataset is used for testing the proposed thermal image super-resolution model.

The KAIST dataset is a collection of video sequences captured in the campus of Korea Advanced Institute of Science and Technology (KAIST). The dataset is used for visual place...

Thermal images, unfazed by extreme lighting conditions unlike visible images, play a pivotal role in applications such as disease diagnosis, military and surveillance,...

MRI images super-resolution reconstruction using deep learning techniques