Adaptive registration and reference-driven spatial attention network for super-resolution of multiframe infrared images

Junyao Zhao; Can Cui; Jun Ke

doi:10.1117/12.3035633

22 November 2024 Adaptive registration and reference-driven spatial attention network for super-resolution of multiframe infrared images

Junyao Zhao, Can Cui, Jun Ke

Author Affiliations +

Proceedings Volume 13240, Holography, Diffractive Optics, and Applications XIV; 132401W (2024) https://doi.org/10.1117/12.3035633
Event: SPIE/COS Photonics Asia, 2024, Nantong, Jiangsu, China

Conference Poster

Abstract

Due to hardware limitations infrared images typically suffer from low resolution and low signal-to-noise ratio. Multi-frame image super-resolution technology exploits the additional information from micro-displacements in multiple low-resolution images to improve image resolution. In this work, we have designed an adaptive registration and reference-driven spatial attention network(ARRSAN) for multi-frame super-resolution. Additionally, a denoising module is integrated into the registration process to mitigate the impact of read shot noise on the registration and super-resolution processes. Results from three datasets, FLIR, Rafael and SIATD demonstrate the performance of our method, even in the presence of noise.

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

Citation Download Citation

Junyao Zhao, Can Cui, and Jun Ke "Adaptive registration and reference-driven spatial attention network for super-resolution of multiframe infrared images", Proc. SPIE 13240, Holography, Diffractive Optics, and Applications XIV, 132401W (22 November 2024); https://doi.org/10.1117/12.3035633

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