In the paper and program implementation, after decomposing the luminance channel, the charbonnier loss is used to calculate the loss, the selection mode is sum, and each decomposition loss is added. If the mode is chosen to be mean, the different layers of the pyramid cannot be summed due to inconsistent sizes. I chose mean and upsampled the pyramid losses of different scales, and added them after the scales were consistent. From this, the return tensor of the mean type is constructed. But the final reconstruction effect is that there are many regular small dots on the image. Do you have any comments?
In the paper and program implementation, after decomposing the luminance channel, the charbonnier loss is used to calculate the loss, the selection mode is sum, and each decomposition loss is added. If the mode is chosen to be mean, the different layers of the pyramid cannot be summed due to inconsistent sizes. I chose mean and upsampled the pyramid losses of different scales, and added them after the scales were consistent. From this, the return tensor of the mean type is constructed. But the final reconstruction effect is that there are many regular small dots on the image. Do you have any comments?