search

yu4u / noise2noise

An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data"
MIT License
1.07k stars 237 forks source link

L0 Loss? #16

Closed PlanesCrossing closed 5 years ago

PlanesCrossing commented 5 years ago

Thanks so much for your implementation.

However I noticed that there is no annealed L0 loss implemented in this current version. Do you plan to update to include this in the future? Especially I notice that L0 showed much better performances in some of the tasks from the original paper.

yu4u commented 5 years ago

Thank you for your suggestion. I'll try later.

yu4u commented 5 years ago

Random-valued impulse noise model and L0 loss were now implemented!

PlanesCrossing commented 5 years ago

This is great, thanks so much!