stalin18

displacement range in correlation and EPE computation

3

Hi, in your paper you wrote that "Correlation with a large displacement (i.e., 40) is performed between conv2a and conv2b" and "correlation with a small displacement (i.e., 20) is performed...

Hi, I am quite new to TensorFlow. I was wondering, why do we need CUDA implementation for this, I mean can't we code a correlation function using Python / TensorFlow...

Hi there, Thank you for sharing this awesome work! I had some question specific to model training and losses: 1. How do you compute gradient in ground-truth image for scale-invariant...

In the `SPADE` class definition here https://github.com/IceClear/StableSR/blob/main/ldm/modules/spade.py, there is a parameter free norm in L77: `self.param_free_norm = normalization(norm_nc)` However, the normalization is a `GroupNorm` with `affine=True` by default, L214 here...