A Regularization by Denoising super-resolution method based on genetic algorithms

作者：

Highlights：

• We treat the multi-frame super-resolution task based on genetic algorithms.

• We propose the use of Nonlocal Means in the regularization term of the Regularization by Denoising cost function.

• The use of genetic algorithms as an optimization approach to search the minimum of the proposed cost function gives better SR reconstruction result compared to other SR techniques.

• The proposed method achieves superior computational performance in terms of PSNR and SSIM measures compared with other approaches.

摘要

•We treat the multi-frame super-resolution task based on genetic algorithms.•We propose the use of Nonlocal Means in the regularization term of the Regularization by Denoising cost function.•The use of genetic algorithms as an optimization approach to search the minimum of the proposed cost function gives better SR reconstruction result compared to other SR techniques.•The proposed method achieves superior computational performance in terms of PSNR and SSIM measures compared with other approaches.

论文关键词：Super-resolution,Genetic algorithms,Nonlocal regularization

论文评审过程：Received 20 February 2019, Revised 11 September 2021, Accepted 12 September 2021, Available online 20 September 2021, Version of Record 23 September 2021.

论文官网地址：https://doi.org/10.1016/j.image.2021.116505