Image super-resolution
Citations
7 citations
7 citations
7 citations
7 citations
Cites background from "Image super-resolution"
...Low rank models and total variation functions are commonly used as regularization function in such inverse problems to stabilize the inversion process [57] [8] [34] [51]....
[...]
...14 and it can be mathematically denoted as, [45, 57], Yk = HkX + Nk , for k = 1 · · ·K (17) where, X is the HR image to synthesize, Hk denotes the combined effect of blurring and down sampling on kth observation Yk , Nk is the noise effects on k th image and K is the number of LR observations....
[...]
7 citations
References
40,609 citations
17,433 citations
16,538 citations
"Image super-resolution" refers background in this paper
...As the l2 norm represents a smoothing prior and the l1 norm tends to preserve the edges, the lp ( ≤ ≤ p 1 2) norm achieves a balance between them, thereby avoiding the staircase effect [110]....
[...]
15,225 citations
"Image super-resolution" refers background in this paper
...[93,103], based on the fact that an image is naturally “blocky” and discontinuous....
[...]
8,009 citations
"Image super-resolution" refers background in this paper
...In the early years, the smoothness of natural images was mainly considered, which leads to the quadratic property of the regularizations [99,100]....
[...]