An Efficient Residual Learning Neural Network for Hyperspectral Image Superresolution
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"
DOI: 10.1109/jstars.2019.2901752
Abstract: Deep learning, especially a discriminative model for image reconstruction, has shown great potential for single image superresolution (SR) of hyperspectral images (HSI). For HSI SR task, it is crucial to predicting each pixel according to… read more here.
Keywords: neural network; image; residual learning; image superresolution ... See more keywords
SD-GAN: Saliency-Discriminated GAN for Remote Sensing Image Superresolution
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Geoscience and Remote Sensing Letters"
DOI: 10.1109/lgrs.2019.2956969
Abstract: Recently, convolutional neural networks have shown superior performance in single-image superresolution. Although existing mean-square-error-based methods achieve high peak signal-to-noise ratio (PSNR), they tend to generate oversmooth results. Generative adversarial network (GAN)-based methods can provide high-resolution… read more here.
Keywords: discriminated gan; remote sensing; saliency discriminated; saliency ... See more keywords
Pyramid Attention “Zero-Shot” Network for Single-Image Superresolution
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Network Science and Engineering"
DOI: 10.1109/tnse.2022.3192471
Abstract: Single-image superresolution (SISR) is one of the requisite image processing methods used to reconstructs a high-resolution (HR) image from a low-resolution (LR) observation. Existing SISR methods mostly rely on supervised learning and are confined to… read more here.
Keywords: network; image superresolution; single image; attention ... See more keywords
Ref‐ZSSR: Zero‐Shot Single Image Superresolution with Reference Image
Sign Up to like & getrecommendations! Published in 2022 at "Computer Graphics Forum"
DOI: 10.1111/cgf.14679
Abstract: Single image superresolution (SISR) has achieved substantial progress based on deep learning. Many SISR methods acquire pairs of low‐resolution (LR) images from their corresponding high‐resolution (HR) counterparts. Being unsupervised, this kind of method also demands… read more here.
Keywords: reference image; reference; single image; image superresolution ... See more keywords