The division of training set and test set in Tanks&Temples dataset

[Xiaohan-Z]

Hello, thank you for your excellent work! But how do we divide the images in the Tanks&Temples dataset into training and test sets to reproduce the results in the paper? Anticipating for your earliest reply!

[ameuleman]

Hi, We preprocess Tanks and Temples scenes as follows: We get the full videos, retain one in every five frames as motion is slow and downscale them to full HD resolution (2048×1080 or 1920×1080), and keep the first 1000 images. Then, we use every tenth frame for testing (i.e. the first, the eleventh, ...). Please let me know if you need further clarification.