Multiscale network combined with multiloss optimization for low-light image super-resolution reconstruction

Bofeng Liu; Haiyang Yu; Xiaojuan Hu; Yanfeng Li

doi:10.1117/12.3048271

3 October 2024 Multiscale network combined with multiloss optimization for low-light image super-resolution reconstruction

Bofeng Liu, Haiyang Yu, Xiaojuan Hu, Yanfeng Li

Author Affiliations +

Proceedings Volume 13272, Fifth International Conference on Computer Vision and Data Mining (ICCVDM 2024); 1327219 (2024) https://doi.org/10.1117/12.3048271
Event: 5th International Conference on Computer Vision and Data Mining (ICCVDM 2024), 2024, Changchun, China

Abstract

The proposed super resolution reconstruction method aims to address the issues of missing detailed information in low light environments and poor recovery of high frequency details in reconstructed images. To fully extract the retained features of low-light images, a multi-scale feature fusion learning network is introduced, which utilizes convolution to extract shallow features and then extracts deep features through multiple cascaded multi-scale feature extraction modules. Additionally, an attention mechanism is incorporated to adaptively learn the importance of each channel and finally fuse the obtained shallow and multi-scale features. Furthermore, perceptual loss and edge loss are integrated into the loss function to optimize the network for high frequency texture details in the recovered image. Experimental results demonstrate that this method yields clearer edge structures and texture details after super-resolution reconstruction of images acquired in low light environments, outperforming other existing methods both visually and objectively.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Bofeng Liu, Haiyang Yu, Xiaojuan Hu, and Yanfeng Li "Multiscale network combined with multiloss optimization for low-light image super-resolution reconstruction", Proc. SPIE 13272, Fifth International Conference on Computer Vision and Data Mining (ICCVDM 2024), 1327219 (3 October 2024); https://doi.org/10.1117/12.3048271

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: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image restoration

Feature extraction

Convolution

Super resolution

Visualization

Image enhancement

Performance modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years