|
|
|
|
|
|
by dimatura
455 days ago
|
|
|
Yes, there are plenty of them. Not sure what the SOTA is, though. Similar to super-resolution, it is relatively simple to create a nearly-infinite dataset for these; pick a clean image, then introduce JPG artifacts. Then train a model to invert the process. |
|
|
Yep, exactly what I was thinking. The thing is it's hard to find enough clean images!