youweixiansheng

1. I think it is a computational trick where 'h_tv' and 'w_tv' will keep the same shape.

2. I am not sure whether the negative values are valid for Gaussian blur or not. Since the gradient map corresponds to the image edge map, I think it might...

`pyramid_addition * alpha/2 + 1` 3. There is an implicit broadcast operator. However, I think that `pyramid_addition * alpha + 1` is enough

`tv_loss = self.mse_loss(self.tv_loss(out_images) , (self.tv_loss(target_images) + self.tv_loss(target_ir)))` where `self.tv_loss` is to compute the sum of the x- and y-axis image gradients. `tv_loss` is designed to keep the gradients of fused...

``` h_tv = torch.pow((x[:, :, 1:, :] - x[:, :, :h_x - 1, :]), 2) ---> h_tv (B×C×H-1×W) w_tv = torch.pow((x[:, :, :, 1:] - x[:, :, :, :w_x -...

`tv_loss = self.mse_loss(self.tv_loss(out_images) , self.tv_loss(target_images))` I agree with you.