Super-Resolution Performance Evaluation Code

The project covers common metrics for super-resolution performance evaluation.

Metrics support

The scripts will calculate the values of the following evaluation metrics: 'MA', 'NIQE', 'PI', 'PSNR', 'BRISQUE', 'SSIM', 'MSE', 'RMSE', 'MAE', 'LPIPS'. Note that the 'SSIM' values are calculated by ssim.m, the matlab code including the suggested downsampling process available in this link.

Highlights

• Breakpoint continuation support : The program can continue from where it was last interrupted by using .xlsx file
• Parallel computing support : The Programs can be re-scaled to take advantage of multi-core performance by using pythonThreadPoolExecutor
• Both RGB and YCbCr color space support

Dependencies

• Python 3
• PyTorch >= 1.0
• Matlab

Instructions for use this code

Please ref BLIND IMAGE QUALITY TOOLBOX

Reference

The code is based on SPSR and BIQT.