How to reproduce the data of LPIPS distance? about bicyclegan HOT 10 CLOSED

For each input image, we produce 20 outputs and compute the distance between each pair of outputs, and take the average. We do this across input images, and take the average.

from bicyclegan.

@richzhang ,thank you, I get the point but still have some questions. Do you compute LPIPS distance between the input image(maps) and the sampled output, or between the corresponding real satellite image and the sampled output?

from bicyclegan.

from bicyclegan.

For each input image, you sample two random codes Z and generated two random outputs at one time. And you do it up to 19 times, i.e., for each input image, you finally get 19 pairs of outputs. After it, you compute LPIPS distance between 19 pairs of outputs and take the average. In your experiment, you do the same operation on 100 inputs and get 1900 pairs of outputs in total, which are used to compute average LPIPS distance. Is it right? @richzhang

from bicyclegan.

Yup! @WorkingCC

from bicyclegan.

@richzhang ,thanks a lot for your patience.

from bicyclegan.

Hi,
Thanks for your great work. For the LPIPS metric, I have one problem, you had tested the LPIPS distance on real images in your corresponding paper, however, as far as I know, there is no paired images in real image set, how can you get that score? Does it mean you compute the distance between random selected real images (not pair, but same domain)?

from bicyclegan.

Yes, they are randomly selected real images. It serves as a "ceiling" -- the results that an algorithm generates given a single A should not be greater than the variation given random ground truth images B.

from bicyclegan.

Yes, I see. Thank you for your patience.

from bicyclegan.

For each input image, you sample two random codes Z and generated two random outputs at one time. And you do it up to 19 times, i.e., for each input image, you finally get 19 pairs of outputs. After it, you compute LPIPS distance between 19 pairs of outputs and take the average. In your experiment, you do the same operation on 100 inputs and get 1900 pairs of outputs in total, which are used to compute average LPIPS distance. Is it right? @richzhang

I think this guy may have some wrong understandings. The right way the collaborator explains is that first you sample 20 images for each real input image, and then you average the distances over all possible pairs of these 20 images which is C_20^2=1900. Finally, this process is repeated over all test images and you get the final score which means if you have n test images, there are 1900 \times n pairs are averaged.

from bicyclegan.