←back to thread

It's easier than ever to de-censor videos

(www.jeffgeerling.com)
387 points DamonHD | 1 comments | 15 Apr 25 17:12 UTC | HN request time: 0.404s | source
Show context
lynndotpy ◴[15 Apr 25 20:19 UTC] No.43697899[source]▶
> Years ago it would've required a supercomputer and a PhD to do this stuff

This isn't actually true. You could do this 20 years ago on a consumer laptop, and you don't need the information you get for free from text moving under a filter either.

What you need is the ability to reproduce the conditions the image was generated and pixelated/blurred under. If the pixel radius only encompasses, say, 4 characters, then you only need to search for those 4 characters first. And then you can proceed to the next few characters represented under the next pixelated block.

You can think of pixelation as a bad hash which is very easy to find a preimage for.

No motion necessary. No AI necessary. No machine learning necessary.

The hard part is recreating the environment though, and AI just means you can skip having that effort and know-how.

replies(4): >>43697947 #>>43698101 #>>43698597 #>>43698629 #
nartho ◴[15 Apr 25 21:27 UTC] No.43698597[source]▶
Noob here, can you elaborate on this ? if you take for example a square of 25px and change the value of each individual pixels to the average color of the group, most of the data is lost, no ? if the group of pixels are big enough can you still undo it ?
replies(6): >>43698743 #>>43698999 #>>43699022 #>>43699023 #>>43699026 #>>43711797 #
1. krackers ◴[17 Apr 25 00:27 UTC] No.43711797[source]▶
As a toy example if you have pixels a,b,c and you blur to (a+b)/2,(b+c)/2, you can recover back c - a. You might be able to have a good estimate of the boundary condition ("a"), e.g. you can just use (a+b)/2 as an approximation for "a", so the recovered result might look fairly close.

You'll basically want to look up the area of deconvolution. You can interpret it in linear algebra terms as trying to invert an ill-conditioned matrix, or in signal processing terms as trying to multiply by the inverse of the PSF. In real-world cases the main challenge is doing so without blowing up any error that comes from quantization noise (or other types of noise).

See https://bartwronski.com/2022/05/26/removing-blur-from-images... and https://yuzhikov.com/articles/BlurredImagesRestoration1.htm