how would the final score be computed?
Why do I see that the top 3 in the rankings are not the highest values of PSNR and SSIM？
As mentioned in "Evaluation":
For the final Perceptual ranking we will conduct a user study to compute Mean Opinion Score (MOS) for the top solutions in the challenge. Due to the complexity of the task we will conduct the user study and compute MOS only for the results submitted for the final test phase. Complementary to MOS, we will report also PSNR and SSIM.
So, the final ranking will be decided based on perceptual quality.
The current ranking in the validation leaderboard has nothing to do with the final ranking.
If you want to sort according to PSNR or SSIM just click on the respective columns and check the relative ranking according to those scores.