Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> Is there a way to "undo" motion blur and get a sharp picture?

Not really, no, any more than there is a way to unblur something that was shot out of focus.

You can play clever tricks with motion estimation and neural networks but really all you're getting is a prediction of what it might have been like if the data had really been present.

Once the information is gone, it's gone.



If the estimation is good it might be enough for some use cases. Is there any software out there that specializes in this? Similarly to maybe AI colorizing or upscaling, which both guess information that is not there anymore.


it's not gone, just more difficult to extract

video has certain temporal statistics which can allow you to fit the missing information

only true blurred white noise is impossible to recover


It really is gone. You can predict what you think it might have been, but you can't know what it was.


it's gone in a single still frame

but across many consecutive frames, the information is spread out temporaly and can be recovered (partially)

the same principle of how you can get a high resolution image from a short video, by extracting the same patch from multiple frames

https://en.wikipedia.org/wiki/Video_super-resolution


No, it's not "restoring detail". The information is gone.

It is predicting what the information might maybe have been like.


you are arguing with math proofs here, the information is not gone, if it was a real video (as opposed to adversarily generated video)

I'm struggling with the idea that you can use maths to recover information from a video that simply was not present in the video.

I get that what you're describing can statisically "unblur" stuff you've blurred with overly-simplistic algorithms.

I can provide you with real-world footage that has "natural" motion blur in it, if you can demonstrate this technique working? I'd really like to see how it's done.


That looks interesting. Is there ready-made software that can do this? Doesn't have to be easy to use just useable with a time commitment of a few days.

> Not really, no, any more than there is a way to unblur something that was shot out of focus.

This is actually possible:

https://en.wikipedia.org/wiki/Deconvolution

If you have a high-quality image (before any compression) with a consistent blur, you can actually remove blur surprisingly well. Not completely perfectly, but often to a surprising degree that defies intuition.

And it's not a prediction -- it's recovering the actual data. Just because it's blurred doesn't mean it's gone -- it's just smeared across pixels, but clever math can be use to recover it. It's used widely in certain types of scientific imaging.

For photographers, it's most useful in removing motion blur from accidentally moving the camera while snapping a photo.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: