About the AFFNET

[Bonnie-gift]

Hi, I am a little confused about the AFFNET. Is the output of the AFFNET the affine transformation predicted? Since I look through the code and find that the input for the AFFNET is only one image. How can the AFFNET predict the affine transformation with one input image.

[ducha-aiki]

The output of AffNet is the "canonical shape" of the local feature (think of SIFT), not the transformation between images.
Please, check the AffNet paper (or any other local feature detection paper such as Hessian-Affine for more information)

[ducha-aiki]

https://kornia-tutorials.readthedocs.io/en/latest/_nbs/image_matching_adalam.html
Check this image from AffNet example. The ellipses in each image are what predicted in AffNet. Then we match them based on local descriptor, thus establishing the correspondence.