Multi-frame GAN-based machine learning image restoration for degraded visual environments

Dennis Estrada; Fraser Dalgleish; Casey Den Ouden; Bing Ouyang

doi:10.1117/12.2587933

12 April 2021 Multi-frame GAN-based machine learning image restoration for degraded visual environments

Dennis Estrada, Fraser Dalgleish, Casey Den Ouden, Bing Ouyang

Proceedings Volume 11730, Big Data III: Learning, Analytics, and Applications; 1173004 (2021) https://doi.org/10.1117/12.2587933
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Although single-frame machine learning image restoration techniques have been shown to be effective, the proposed multi-frame approach takes advantage of both spatial and temporal information to resolve high-resolution and high-dynamic-range images. The proposed algorithm is an extension of the previously proposed algorithm DeblurGAN-C and aims to further improve the capabilities of image restoration in degraded visual environments. The main contributions of the proposed techniques include: 1) Development of an effective framework to generate a multi-frame training dataset typical of degraded visual environments; 2) Adopting a multi-frame image restoration framework that generates a single restored image as the output; 3) Conducting substantial experiments against the generated multi-frame training dataset and demonstrate the effectiveness of the proposed multi-frame image enhancement algorithm.

Conference Presentation

Citation Download Citation

Dennis Estrada, Fraser Dalgleish, Casey Den Ouden, and Bing Ouyang "Multi-frame GAN-based machine learning image restoration for degraded visual environments", Proc. SPIE 11730, Big Data III: Learning, Analytics, and Applications, 1173004 (12 April 2021); https://doi.org/10.1117/12.2587933

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