en
0.25
0.5
0.75
1.25
1.5
1.75
2
Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding
Published on Oct 09, 20125298 Views
This paper describes a single-image super-resolution (SR) algorithm based on nonnegative neighbor embedding. It belongs to the family of single-image example-based SR algorithms, since it uses a dic
Related categories
Chapter list
Low-complexity single-image super-resolution based on nonnegative neighbor embedding00:00
Overview00:10
Single-image Super-Resolution00:36
Methods01:10
Nearest Neighbor SR02:40
LLE-based Nearest Neighbor SR04:30
Key points06:07
[KP1] Representation by features06:27
[KP1] Analysis of the features07:15
[KP1] Why the fall?08:58
[KP2] A nonnegative embedding?10:25
[KP2] Analysis of the weights11:00
[KP3] Choice of the dictionary12:17
Algorithm: summary13:29
Experiments: algorithms considered14:09
Results 1/314:46
Results 2/315:03
Results 3/315:48
Visual results: bird 1/616:14
Visual results: bird 2/616:20
Visual results: bird 3/616:23
Visual results: bird 4/616:25
Visual results: bird 5/616:28
Visual results: bird 6/616:30
Visual results: baby 1/616:32
Visual results: baby 2/616:34
Visual results: baby 3/616:36
Visual results: baby 4/616:37
Visual results: baby 5/616:40
Visual results: baby 6/616:43
Conclusions16:51
Thanks17:33