A progressive approach for single image super-resolution

Yongbo Liang; Guo Cao; Xuesong Li

doi:10.1117/12.2540564

31 July 2019 A progressive approach for single image super-resolution

Yongbo Liang, Guo Cao, Xuesong Li

Proceedings Volume 11198, Fourth International Workshop on Pattern Recognition; 1119805 (2019) https://doi.org/10.1117/12.2540564
Event: Fourth International Workshop on Pattern Recognition, 2019, Nanjing, China

Abstract

Convolutional neural network has achieved excellent success in single image super-resolution. In this paper, we present a progressive approach which reconstructs a high resolution image and optimizes the network at each level. In addition, our method can generate multi-scale HR image by one feed-forward network. The proposed method also utilizes the relationships among different scales, which help our network perform well on large scaling factors. Experiments on benchmark dataset demonstrate that our method achieves competitive performance against most state-of-the-art methods, especially for large scaling factors (e.g. 8×).

Citation Download Citation

Yongbo Liang, Guo Cao, and Xuesong Li "A progressive approach for single image super-resolution", Proc. SPIE 11198, Fourth International Workshop on Pattern Recognition, 1119805 (31 July 2019); https://doi.org/10.1117/12.2540564

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available