search

tamarott / SinGAN

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"
https://tamarott.github.io/SinGAN.htm
Other
3.29k stars 608 forks source link

About calculating PSNR after super-resolution #73

Open 15732031137 opened 4 years ago

15732031137 commented 4 years ago

Hello! First of all, congratulations on your paper getting the best ICCV paper, thank you for your contribution to GAN network research, and share your code. I have had the honor to study your paper and program recently. I see that you have a picture with a size of 80 120, and then the size of the image becomes 320 480 after super resolution. The number of pixels or the size of the two pictures are different. I would like to ask you how to calculate the two The picture's peak signal-to-noise ratio (PSNR)?

tamarott commented 4 years ago

All the SR evaluation were done using the code of the work "the perception-distortion tradeoff" by Blau et. al. Code is available at their project webpage: https://webee.technion.ac.il/people/tomermic/PerceptionDistortion/PD_tradeoff.htm

junxiant commented 2 years ago

Hello! First of all, congratulations on your paper getting the best ICCV paper, thank you for your contribution to GAN network research, and share your code. I have had the honor to study your paper and program recently. I see that you have a picture with a size of 80 120, and then the size of the image becomes 320 480 after super resolution. The number of pixels or the size of the two pictures are different. I would like to ask you how to calculate the two The picture's peak signal-to-noise ratio (PSNR)?

Hi,

Did you manage to calculate the PSNR?