Learning to perform joint image super-resolution and rain removal via a single-convolutional neural network

Di Zhang; Jiazhong He; Yun Zhao

doi:10.1117/1.JEI.27.6.063024

15 December 2018 Learning to perform joint image super-resolution and rain removal via a single-convolutional neural network

Di Zhang, Jiazhong He, Yun Zhao

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 6, 063024 (December 2018). https://doi.org/10.1117/1.JEI.27.6.063024

Abstract

In outdoor low-level vision systems, not only is the resolution of the imaging system important, but rain corrupts the visibility of outdoor scenes and may cause computer vision systems to fail. We present a deep convolutional neural network (CNN) architecture for simultaneously performing single-image super-resolution and rain removal. Instead of learning an end-to-end mapping between the low-resolution rainy images and high-resolution clean images in the original image space, we train our network in the detail space, i.e., the space obtained by high-pass filtering the original image. The proposed CNN has a lightweight structure, yet it outperforms super-resolution and rain removal consecutively by a significantly large margin (>1 dB on average).

Citation Download Citation

Di Zhang, Jiazhong He, and Yun Zhao "Learning to perform joint image super-resolution and rain removal via a single-convolutional neural network," Journal of Electronic Imaging 27(6), 063024 (15 December 2018). https://doi.org/10.1117/1.JEI.27.6.063024

Received: 25 July 2018; Accepted: 20 November 2018; Published: 15 December 2018

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