Image2Image model

[advimman]

Image2Image model

[windj007]

Hi! Sorry for the late reply.

do you have any suggestions on how to modify the loss functions for better detail perservation?

The answer would depend very much on the task and the dataset. Given more details, I can probably recommend something.

[armheb]

Thanks for your reply. Basically, I'm using the lama to get rid of some artifacts in my images. Below is an example image

.
from left to right is the input image, target, and lama output. as seen above I'm losing some of the details in the texture and images on the shirt. I was hoping to modify the loss functions to better preserve these features in the input image. Thanks.

[windj007]

I see.. I think that this task is pretty different from what Lama was deisgned for - so you probably need to change not only losses, but also architecture and data generation process. There are plenty of possible options to try from stochasticity in generator to custom perceptual losses.

Also, it seems that FFC is a bit meaningless in that task - in inpainting it increases receptive field and helps to capture patterns - but in this example mostly local information is relevant.

[armheb]

Thanks, Yes I have changed the data generation process and architecture. I'll also try custom perceptual losses too. Thank you.