Closed wangchust closed 3 years ago
Hi @wangchust, thanks for your interest in our work. We follow the settings widely used in existing SR methods (e.g., RCAN) for performance evaluation. The convert coefficients are used to calculate the luminance channel and the borders are shaved for fair comparison. For SSIM, we modified the code from BasicSR.
I've got it. Thanks for yours explanation
Hi, author. Thank you for your excellent work. But I'm a little confused about the code which calculate PSNR and SSIM metric. For PSNR, why the diff is multipide by a convert coefficient and shave the border when benchmarch is set to True. For SSIM, why not directly use api from skimage? Waiting for your response, sincerely.