Face super-resolution via multilayer locality-constrained iterative neighbor embedding and intermediate dictionary learning
Based on the assumption that low-resolution (LR) and high-resolution (HR) manifolds are locally isometric, the neighbor embedding super-resolution algorithms try to preserve the geometry (reconstruction weights) of the LR space for the reconstructed HR space, but neglect the geometry of the original...
| Publié dans: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 23(2014), 10 vom: 27. Okt., Seite 4220-31 |
|---|---|
| Auteur principal: | |
| Autres auteurs: | , , |
| Format: | Article en ligne |
| Langue: | English |
| Publié: |
2014
|
| Accès à la collection: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |
| Sujets: | Journal Article Research Support, Non-U.S. Gov't |
| Accès en ligne |
Volltext |