Mathematical Analysis of DCN-Based Super-Resolution

C. Lee; J. Park; S. Woo; J. Kim; J. Yoon

doi:10.1109/ACCESS.2020.2992483

IEEE Access (Jan 2020)

Mathematical Analysis of DCN-Based Super-Resolution

C. Lee,
J. Park,
S. Woo,
J. Kim,
J. Yoon

Affiliations

C. Lee: ORCiD; School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea
J. Park: School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea
S. Woo: ORCiD; School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea
J. Kim: School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea
J. Yoon: School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea

DOI: https://doi.org/10.1109/ACCESS.2020.2992483
Journal volume & issue: Vol. 8
pp. 90420 – 90429

Abstract

Read online

Although DCN-based super-resolution (DCN-SR) techniques have shown impressive performance, the working mechanism has not been completely understood and DCN-SR methods still produce some artefacts. In this paper, we analyze the working mechanisms of DCN-SR methods. We derive mathematical formulations of the DCN-SR methods and provide some experimental analyses, which show that the effective receptive fields of the DCN-SR methods are considerably smaller than the theoretical receptive fields. Based on the mathematical formulations, experiments were performed. The results indicates that current DCN-SR methods may have some fundamental problems and new types of DCN structures are needed for reliable super-resolution performance.

Published in IEEE Access

ISSN: 2169-3536 (Online)
Publisher: IEEE
Country of publisher: United States
LCC subjects: Technology: Electrical engineering. Electronics. Nuclear engineering
Website: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639

About the journal

Abstract

Keywords