Image super-resolution
Citations
991 citations
590 citations
Cites background from "Image super-resolution"
...Image super-resolution, reconstructing a higher-resolution image or image sequence from the observed low-resolution image [190], is an exciting application of deep learning methods....
[...]
305 citations
240 citations
203 citations
Cites background from "Image super-resolution"
...Instead of devoting to physical imaging technology, many researchers aim to recover highresolution images from low-resolution ones using an image processing technology called super-resolution [1]....
[...]
References
253 citations
253 citations
249 citations
Additional excerpts
...However, the optical flow based methods are computationally expensive [141] and are sensitive to noise, large displacements, and illumination variation [142]....
[...]
236 citations
"Image super-resolution" refers background or methods in this paper
...It appears that LDFPI and IRN are two different methods; however, they are almost the same in essence when dealing with the −l norm1 problem by smooth approximation....
[...]
...IRN is a method which can minimize the lp norm ( ≤ p 2) by approximating it with a weighted l2 norm [129]....
[...]
...The representative algorithms include lagged diffusivity fixed point iteration (LDFPI) [128], majorization-minimization (MM) [104], the iteratively reweighted norm (IRN) [129,132], and the half-quadratic algorithm [95]....
[...]
...The notations are based on LDFPI [128] and IRN [129], respectively....
[...]
...fixed point iteration (LDFPI) [128], majorization-minimization (MM) [104], the iteratively reweighted norm (IRN) [129,132], and the half-quadratic algorithm [95]....
[...]
236 citations