About patch_select

[Lcz]

Hi, @Tengfei-Wang

First of all, I want to say thank you and ask you again.

Because the released codes are only training the overlapped FoV on CameraFusion.

So when training on CUFED5, I changed L_x to L_x = random.randrange(0, L_w - L_p + 1 - 15) for training the whole image.

When testing, I directly use the same corresponding position between the reference image and input image as a patch_ref because I think input image and reference image are very similar.

So in the second for loop, I remove those lines and select the pixel value of patch_ref[] to 4x patch_LR in the same corresponding position and set course as False.

But the result is not good, I feel my choice of patch_ref is too simple, how can I do to achieve the result in the paper when training CUFED5?

Looking forward to your reply!

[Tengfei Wang]

Hi,
For CUFED5, we use the full ref image for inference (instead of a patch).

[Lcz]

Hi, @Tengfei-Wang

Did you mean to use the full ref image only during the testing and use patch during the training ?

Thanks in advance!