Iterative attribute augmentation network for face image super resolution

Abstract Although recently a series of deep‐learning based methods have promoted the performance of face super resolution (FSR), most of these methods cannot recover essential face attributes accurately, especially to super‐resolve a very low‐resolution (LR) face image (16×16 pixels) to its (8×) hig...

Full description

Bibliographic Details

Published in:	Electronics Letters
Main Authors:	Zi Teng, Xiaosheng Yu, Chengdong Wu
Format:	Article
Language:	English
Published:	Wiley 2021-10-01
Subjects:	Optical, image and video signal processing Image recognition Computer vision and image processing techniques
Online Access:	https://doi.org/10.1049/ell2.12285