Learning image block statistics and quality assessment losses for perceptual image super-resolution

Sheng Tian; Lian Zou; Ye Yang; Chuishun Kong; Yifeng Liu

doi:10.1117/1.JEI.28.1.013042

19 February 2019 Learning image block statistics and quality assessment losses for perceptual image super-resolution

Sheng Tian, Lian Zou, Ye Yang, Chuishun Kong, Yifeng Liu

Author Affiliations +

Journal of Electronic Imaging, Vol. 28, Issue 1, 013042 (February 2019). https://doi.org/10.1117/1.JEI.28.1.013042

Abstract

The loss function plays an important role in model training for the single-image super-resolution task. Most convolutional neural network-based models adopt conventional pixel-wise loss functions to make impressive advances in peak signal-to-noise ratio and structural similarity index. However, these losses tend to find the average of plausible solutions, which lead to overly smoothed SR results with a lower visual perception. We propose a loss function combining the statistics loss with semantic priors and the quality assessment loss to produce an HR image with high visual quality while maintaining natural image statistics, as perceived by human observers. Our statistics loss measures the similarity of deep feature distributions in different semantic blocks and contributes to the maintenance of natural internal statistics in image restoration. Additionally, a no-reference quality metric that focuses on several aspects of human perceptual preferences for lighting, tone, and sharpness is introduced in our loss function to provide a more visually compelling approximation of human visual perception for perceptual image super-resolution. Experiments prove that our loss function can effectively guide the network to generate images of high-perceptual quality while considering the structural distortion for single-image super-resolution.

Citation Download Citation

Sheng Tian, Lian Zou, Ye Yang, Chuishun Kong, and Yifeng Liu "Learning image block statistics and quality assessment losses for perceptual image super-resolution," Journal of Electronic Imaging 28(1), 013042 (19 February 2019). https://doi.org/10.1117/1.JEI.28.1.013042

Received: 6 November 2018; Accepted: 1 February 2019; Published: 19 February 2019

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

Members: $24.00

Non-members: $28.00 ADD TO CART

JOURNAL ARTICLE
15 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image quality

Gallium nitride

Image segmentation

Super resolution

Visualization

Signal attenuation

Feature extraction

Show All Keywords

Keywords/Phrases

Search In:

Publication Years