Oh, here's a good use for NNs. Making nearly photorealistic 3D scenes (with people) look actually photorealistic, as post processing.
maybe applying an existing super-resolution model would do the trick
-
-
super-resolution style is supervised learning, it would require the ground truth during training
-
not that this is problem, and it will probably give the best results, but can we do that w/out strong supervision?
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.