IEEE Access (Jan 2023)

F2SRGAN: A Lightweight Approach Boosting Perceptual Quality in Single Image Super-Resolution via a Revised Fast Fourier Convolution

  • Duc Phuc Nguyen,
  • Khanh Hung Vu,
  • Duc Dung Nguyen,
  • Hoang-Anh Pham

DOI
https://doi.org/10.1109/ACCESS.2023.3260159
Journal volume & issue
Vol. 11
pp. 29062 – 29073

Abstract

Read online

With the successful development of deep learning, single image super-resolution (SISR) has advanced significantly in recent years. However, in practice, excessive convolutions limit super-resolution applications on platforms with limited resources like mobile devices or embedded systems. Besides, existing lightweight models have a problem with small receptive fields and only consider local features for the reconstruction. Previous models try to stack more convolutions layers to address this problem, but this prolongs the execution time due to increasing the number of parameters. Therefore, this paper proposes a novel approach named F2SRGAN using a revised Fast Fourier Convolution to enlarge the receptive field, enabling this model to learn global features better, neither introducing too many parameters nor prolonging the model inference time. The experimental results show that our proposed F2SRGAN significantly improves perceptual image quality among the lightweight SISR methods while maintaining an acceptable inference time.

Keywords