Neural net architectures for image demosaicing

Rhys Buggy; Marco Forte; François Pitié

doi:10.1117/12.2322353

17 September 2018 Neural net architectures for image demosaicing

Rhys Buggy, Marco Forte, François Pitié

Proceedings Volume 10752, Applications of Digital Image Processing XLI; 1075218 (2018) https://doi.org/10.1117/12.2322353
Event: SPIE Optical Engineering + Applications, 2018, San Diego, California, United States

Abstract

Demosaicing remains a critical component of modern digital image processing, with a direct impact on image quality. Conventional demosaicing methods yield relatively poor results especially light-weight methods used for fast processing. Alternatively, recent works utilizing Deep Convolutional Neural Nets have significantly improved upon previous methods, increasing both quantitative and perceptual performance. This approach has seen significant reduction of artifacts but there still remains scope for meaningful improvement. To further this research, we investigate the use of alternate architectures and training parameters to reduce incurred errors, especially visually disturbing demosaicing artifacts such as moiré and provide an overview of current methods to better understand their expected performance. Our results show a U-NET style Network to outperform previous methods in quantitative and perceptual error and remain computationally efficient for use in GPU accelerated applications as an end-to-end demosaicing solution.

Conference Presentation

Citation Download Citation

Rhys Buggy, Marco Forte, and François Pitié "Neural net architectures for image demosaicing", Proc. SPIE 10752, Applications of Digital Image Processing XLI, 1075218 (17 September 2018); https://doi.org/10.1117/12.2322353

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