Text this: Learning transformation invariance for pairwise image matching

 _    _    _    _     ______    _____     ____    
| || | || | || | ||  /_   _//  |  ___||  |  _ \\  
| || | || | || | ||    | ||    | ||__    | |_| || 
| \\_/ || | \\_/ ||   _| ||    | ||__    | .  //  
 \____//   \____//   /__//     |_____||  |_|\_\\  
  `---`     `---`    `--`      `-----`   `-` --`