neural-enhance

If you're talking about https://github.com/alexjc/neural-enhance it's NOT "pulling out" existing details from photos. It's making up details.

I recently found a little script called [1] "enhance" that uses AI to enhance an input image. Anyway it conveniently runs as a docker script and you can set use it via a bash alias. alias enhance='function ne() { docker run --rm -v "$(pwd)/`dirname ${@:$#}`":/ne/input -it alexjc/neural-enhance ${@:1:$#-1} "input/`basename ${@:$#}`"; }; ne' Sp when I run "$ enhance 'my_image.png' " in my terminal, it downloads the image (if they're not there) and executes the program seamlessly. I thought this was pretty cool as the only dependency your system needs is Docker and all your aliases will resolve when/if they're used. Of course this is not super efficient and may only be useful for certain situations but I think it's a nice way to work. So I'm looking for a list of useful CLI apps that run with docker images, so I can build a list of ali

You can enhance the overall image quality using: https://github.com/alexjc/neural-enhance on every frame. https://letsenhance.io/ For faces: https://www.geoffreylitt.com/2017/06/04/enhance-upscaling-im...

It may or may not work, but try applying the below project to a few frames to see what you get. Make sure to preserve the original footage on the original media, though. https://github.com/alexjc/neural-enhance

That's the point of using deep learning here. Of course you can't make up the missing information, but by training the model with a lot of samples, it should eventually reach a point where it produces the most likely original information. It works quite well on images: https://github.com/alexjc/neural-enhance

Here's a list of various image interpolation techniques: - http://www.ifp.illinois.edu/~jyang29/papers/chap1.pdf * Image super-resolution: Historical overview and future challenges - http://www.robots.ox.ac.uk/~vgg/publications/papers/pickup08... * Machine Learning in Multi-frame Image Super-resolution - http://www.cs.huji.ac.il/~peleg/papers/icpr90-SuperResolutio... - http://www.wisdom.weizmann.ac.il/~vision/SingleImageSR.html - http://chiranjivi.tripod.com/EDITut.html - http://www.tecnick.com/pagefiles/appunti/iNEDI_tesi_Nicola_A... - http://www.eurasip.org/Proceedings/Eusipco/Eusipco2009/conte... - http://bengal.missouri.edu/~kes25c/ * http://bengal.missouri.edu/~kes25c/nnedi3.zip * http://forum.doom9.org/showthread.php?t=147695 - http://arxiv.org/pdf/1501.00092v2.pdf * http://waifu2x.udp.jp/ * https://github.com/nagadomi/waifu2x * h

We all laughed at the ridiculous "Zoom and Enhance" bits on TV crime shows, but it's become much more plausible in the past couple of years. It's called super-resolution, or upsampling. Here is a good overview of techniques: http://www.robots.ox.ac.uk/~vgg/publications/papers/pickup08... More recently, Google's RAISER: https://research.googleblog.com/2016/11/enhance-raisr-sharp-... This repo pulls together techniques from several papers with impressive results: https://github.com/alexjc/neural-enhance Anyway, it's an area of active research, there are already four dozen relevant papers in 2017 alone: https://scholar.google.com/scholar?q="machine+learning"+"sup...

One of my favorites is Neural Enhance: https://github.com/alexjc/neural-enhance I was playing around with it and the results are quite interesting. It's pretty much exactly what you describe. The nice thing is, if you have Docker installed, you can run: docker run --rm -v `pwd`:/ne/input -it alexjc/neural-enhance --help and everything magically works. Compared to other machine learning projects, neural enhance is probably one of the easiest to get started with.

The example w/ the Japanese ideograms is impressive, it seems to actually make a difference on readability. https://github.com/alexjc/neural-enhance/blob/master/docs/St...