xinntao/ESRGAN
1
1
Fork 0
mirror of https://github.com/xinntao/ESRGAN.git synced 2024-08-17 00:20:32 +03:00
Code Issues Projects Releases Wiki Activity

reference to the PIRM18-SR Chanllenge report

Browse Source
This commit is contained in:
Xintao 2018-11-08 21:52:51 +08:00 committed by GitHub
parent 819ff1d216
commit 24eca1d826
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
QA.md
View File

@ -6,6 +6,8 @@ First, the released ESRGAN model in the GitHub (`RRDB_ESRGAN_x4.pth`) is **diffe
We found that the lower perceptual index does not always guarantee a better visual quality. We found that the lower perceptual index does not always guarantee a better visual quality.
The aims for the competition and our ESRGAN work will be a bit different. The aims for the competition and our ESRGAN work will be a bit different.
We think the aim for the competition is the lower perceptual index and the aim for our ESRGAN work is the better visual quality. We think the aim for the competition is the lower perceptual index and the aim for our ESRGAN work is the better visual quality.
> More analyses can be found in Sec 4.1 and Sec 5 in [PIRM18-SR Chanllenge report](https://arxiv.org/pdf/1809.07517.pdf).
> It points out that PI (perceptual index) is well correlated with the human-opinion-scores on a coarse scale, but it is not always well-correlated with these scores on a finer scale. This highlights the urgent need for better perceptual quality metrics.)
Therefore, in the PIRM18-SR Challenge competition, we used several tricks for the best perceptual index (see Section 4.5 in the [paper](https://arxiv.org/abs/1809.00219)). Therefore, in the PIRM18-SR Challenge competition, we used several tricks for the best perceptual index (see Section 4.5 in the [paper](https://arxiv.org/abs/1809.00219)).