… or can be estimated within subpixel accuracy … images compared to the reference LR image
are estimated with fractional pixel accuracy. Obviously, accurate subpixel motion estimation is …

… A popular family of estimators are the ML-type estimators (M estimators) [18]. We rewrite
the definition of these estimators in the super resolution context as the following minimization …

… high-resolution images that are competitive or even superior in quality to images produced
… from the previously mentioned optimization as our final estimate of the high-resolution image…

… as motion estimation, and the blurring function estimation. We start with a single highquality …
We demonstrate that, indeed, there is an ability to restore an image with improved resolution…

… The straightforward way is to feed multi-resolution images separately into multiple networks
and aggregate the output response maps [62]. Hourglass [39] and its extensions [74, 30] …

… of generating a superresolution (SR) image from a single low-resolution input image. We
approach this … Joint MAP registration and high-resolution image estimation using a sequence of …

… The highly challenging task of estimating a highresolution (HR) image from its low-resolution
(LR) counterpart is referred to as super-resolution (SR). SR received substantial attention …

… In this case, the estimation of g should be impossible because of the restriction of image
resolution. Furthermore, the quantization noise will severely affect the estimation when cr is very …

… preserving prior image model is used to extract a high-resolution video still given a short
low-resolution sequence. Estimates computed from a low-resolution image sequence …

… , the estimation of a high resolution pixel … estimation of network parameters Q ¼ fW1;W2;W3;B1;
B2;B3g. This is achieved through minimizing the loss between the reconstructed images …