think open source + behind the scenes.
the plan is to share code, papers, science, thoughts in the making, research, etc. but all around well defined projects to be pragmatic.
if you already like projects like Keras, this may be a nice place to checkout what you can do with it.
yeah, its from less than an hour ago :D
We will add the welcome messages and everything else.
But please, feel free to introduce yourself in the project that you think is interesting and get a conversation started.
this is supposed to be used in the data processing step. you load your image from jpeg or your video using ffmpeg, enhance the images and then pass it to the next step where color rendering is done. you can do that in the browser or mobile just as fine.
yeah, no AI. Its low level computer vision. There is no implicit understanding of the scene to enhance it here. We show the neural nets several examples of low and high quality images it learns a function that makes the low quality looks more like the high quality.
this may make you feel disappointed now, but in the write up we are also pitching this same module to be used in generative networks and other models that do build an understanding of the scene. Lets see what the community (and ourselves) can do next...
Wait, the neural network encodes within itself probability distributions of the various image patches it has seen. This is sort of like AI.
Approaches in the past used heuristics (like finding edges and upsampling them, etc). Those were fragile systems. In this approach, the system learns what's appropriate on its own.
I'm glad to hear that, I feared it might just paste any eyes where it sees some eyes, but like this it might be much closer to what is really in the pixels.
yup, to certain point! there are information theoretic limits though. You can fill in information, but there will be biases to a certain point. in this case defined by the dataset. if the "enhance" is too strong, we should be careful with what we do with the results in forensics.
but man, it can make your internet pics look smooth! :)
thanks for the comment!
If you have multiple images of the same scene (for example, from video frames), you should be able to use information across frames for a true enhancement?
Hi, sorry for the poor documentation. But please, check out the paper the person above mentioned. We worked hard to make it as accessible as possible. Also, the core of our code is actually here: https://github.com/EderSantana/seya/blob/master/seya/layers/...
If you are a Keras (or Theano) dev it should be an easy read. If not, please drop us a note on github.
