igv

Yes, SSIM normally used with mean pooling and it's usually useless, because it's wrong. > I wonder if it could be useful as a loss function. You will probably have...

> To be honest, I'm surprised that the first layer is 7 times less significant than second. Agree. I've experimented with only 2 scales (`WEIGHTS = [0.2, 0.8]`) and it...

I've used images from [this](https://storage.googleapis.com/demos.webmproject.org/webp/cmp/2021_12_15/index.html) comparison and compared results to [VIFp](https://github.com/Netflix/vmaf/issues/826#issuecomment-781923811) (I think now I prefer this metric over MS-SSIM).