Question about the calculation of psnr

[zhangjing128]

Hi @m-tassano ,
Recently I tried to reproduce your work and found that the denoise effect performed well visually. But the PSNR value is not satisfactory. Here are some questions about PSNR. I will be very grateful to you if you can give me some advice.

1. As you mentioned, "the PSNR displayed on the paper is the average of the PNSR of each sequence in the testset. The PSNR of each sequence is the average of the PSNR of all frames" (link: Can you help me to reproduce your result? #13 (comment)), I am wondering is it ok to calculate the video's PNSR using the average value? For example, my video only has two frames. The 1st frame of the video is a cat, and the 2nd frame of the video is a dog. So the PNSR(video) = [ PSNR(cat) + PSNR(dog) ] / 2 ?
   I mean sometimes the different objects may be photoed very differently and make different levels of noise(due to the material of the object surface, illumination, etc.) If each frame changes greatly, is it appropriate to use the average value to represent the overall denoising effect? I'm not sure whether some other factors need to be taken into account when calculating the video denoising effect.
2. The link you provided here cannot be accessed now (https://www.dropbox.com/s/wei8uhym1i4viot/make_tables_allalgos.ipynb?dl=0) from your answer: Can you help me to reproduce your result? #13 (comment). Could you please send a new link about the calculation of the metrics? By the way, I have read some of your code and I think the way you calculate the PSNR has been contained in the project (utils.py). Do we need to calculate again using the link above ( provided in the dropbox )?

Thank you for reading here patiently. Wish you have a good day :)

[m-tassano]

Hi,
Thanks for the interest in the paper. I answer to your points below

1. The algorithm was designed mainly to denoise video sequences captured with a camera. In this context, the use of the mean psnr is justified as there won't be changes in the input as large as the ones you mention. In any case, you can settle for the flavor of pnsr you prefer as long as you are coherent and use the same type whenever you want to compute the metric.
2. You can check https://gist.github.com/m-tassano/1ea99ec8fdbaae956a77938a98424463
   Hope this helps

[zhangjing128]

Got it. Thank you for your kind help :) 👍 !