News for hackers. Stuff that matters.
Re:FastMRI leverages adversarial training to remove image ar... by throwlaplace on Tuesday February 25, 2020 @03:26PM (#22417074)
Isn't this basically SRGAN?

Edit: sorry I guess since there's an explicit rotation module it's closer to SRGAN+deformable convolutions.

Re:FastMRI leverages adversarial training to remove image ar... by zn473 on Tuesday February 25, 2020 @05:16PM (#22418080)
The adversary in this work never sees non-reconstructed images, so it looks like it's completely unrelated to SRGAN.