QSRNet: towards quaternion-based single image super-resolution

Shreyas Kamath K. M.; Shishir Paramathma Rao; Karen Panetta; Sos S. Agaian

doi:10.1117/12.2618542

27 May 2022 QSRNet: towards quaternion-based single image super-resolution

Shreyas Kamath K. M., Shishir Paramathma Rao, Karen Panetta, Sos S. Agaian

Proceedings Volume 12100, Multimodal Image Exploitation and Learning 2022; 121000I (2022) https://doi.org/10.1117/12.2618542
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Conference Poster

Abstract

Single-image super-resolution (SISR), which maps a low-resolution observation to a high-resolution image, has been extensively utilized in various computer vision applications. With the advent of convolutional neural networks (CNNs), numerous algorithms have emerged that achieve state-of-the-art results. However, the main drawback of CNN is the negligence in the interrelationship between the RGB color channel. This negligence further reduces crucial structural information of color and provides a non-optimal representation of color images. Furthermore, most of these CNN-based methods contain millions of parameters and layers, limiting the practical applications. To overcome these drawbacks, an endto- end trainable single image super-resolution method – Quaternion-based Image Super-Resolution network (QSRNet) that takes advantage of the quaternion theory is proposed in this paper. QSRNet aims at maintaining the local and global interrelationship between the channels and produces high-resolution images with approximately 4x fewer parameters when compared to standard CNNs. Extensive computer experimentations were conducted on publicly available benchmarking thermal datasets, including DIV2K, Flickr2K, Set5, Set14, BSD100, Urban100, and UEC100, to demonstrate the effectiveness of the proposed QSRNet compared to traditional CNNs.

Citation Download Citation

Shreyas Kamath K. M., Shishir Paramathma Rao, Karen Panetta, and Sos S. Agaian "QSRNet: towards quaternion-based single image super-resolution", Proc. SPIE 12100, Multimodal Image Exploitation and Learning 2022, 121000I (27 May 2022); https://doi.org/10.1117/12.2618542

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