Well, it’s not jpeg, however you could use it to reduce the size of neural networks for image generation or whatever.
1 Like
A natural image for example has some randomness but also has a lot of embedded order. For example a lot of sine and cosine embedded waves. And those can be extracted to do things like jpeg compression.
You can go the other way though and randomly flip the signs of the data in the natural image. If you go looking for embedded sine and cosine waves you won’t find any. Instead you will find Gaussian noise from the Normal random distribution.
Are those random numbers useless? No, on the contrary each single one of them contains its fair share of information about all the natural image. And you only need pick a few of them, it doesn’t matter which, do some inversion and smoothing a few times and you get some reasonable representation of the original image back.
1 Like
I got a nice improvement by doubling the quality of the random projections:
https://editor.p5js.org/seanhaddps/sketches/ahSgFi6ue
1 Like
Interesting discussion! While the approach you’re sharing is not traditional JPEG compression, it sounds fascinating for optimizing neural networks. I use https://jpegcompressor.com/. It’s a simple tool for compressing images without losing quality, which might be useful in different image-related projects."
Confidence level: High