about OP dataset

[sofa]

Thanks for sharing the OP dataset.

When I was using the dataset, I found that each line under the splits/train_split.txt file points to 4 files,
for example, 28.5366_-81.3741_nadir.png,28.53663_-81.37406.png,28.5366_-81.3741.png,28.53663_-81.37406.png.
Whereas each line in splits/test_split.txt points to only two files per line,
For example, 40.44_-80.0005_nadir.png,40.44001_-80.00056.png.

How are the four files in each line of train_split.txt trained? It seems that the third file in each line of train_split.txt does not exist, while the fourth file has the same file name as the second file.

[Krishna Regmi]

The first two filenames represent the aerial and the ground images, the third file name was used for GAN generated images in my experiments. As you pointed out correctly, fourth one is the same as the second and isn't used in training.
If you do not have extra inputs in your experiments and want to use only aerial and ground images, you would use the first two file names only during the training.
Hope this helps!