Photoshop 'unblur' leaves MAX audience gasping for air • Hacker News Board

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#71

Post by ibuildthings » Tue, Oct 11, 2011, 10:05 AM UTC

mey wrote: post #30

Geee wrote: post #24

It's called blind deconvolution. Blind means that they have to first estimate the original convolution/blur kernel and in the second phase, apply the deconvolution. If there's acceleration sensor on the camera, you can use data from that for the blur kernel. It's nothing new really, but algorithms for it have advanced tremendously. For example, there's some results from 2009 http://www.youtube.com/watch?v=uqMW3OleLM4…

Does this algorithm lend itself to video? Probably would take a massive cloud of systems to correct any highdef video signal, but it would be impressive for many applications (news broadcast, sports, or any live event, security, or remote robots) Granted to achieve performance on the order of near realtime dsp, it would require an impressive hardware system. Then again, when I can spend the price of a coffee and get…

Actually human eye/brain is much more forgiving to motion blur in video that in still images. The chances are that one will spot quite a number of artifacts [compression as well as blur] in a grabbed frame of an HD quality video, which is otherwise unacceptable in a photograph.

In theory, you can tweak this method such that it is run in parallel frames 'almost' independently. I say 'almost' since you will have to factor in temporal coherence, such that deconvolution kernels do not vary much between subsequent frames (otherwise it will cause unwarranted flicker and jitter like effects)

However, more pertinent and related problem with respect to video is that of image stabilization. And computer vision community is making some exciting strides in the front; for eg: http://web.cecs.pdx.edu/~fliu/ .

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#72

Post by ibuildthings » Tue, Oct 11, 2011, 10:13 AM UTC

One of the tricky thrones in this method is extracting/guessing the camera motion path purely from image measurements. Better the estimate, the better the deblur kernel will be. What might be cool is if they can extract out meta-information using some kind of inertial and gyroscope-akin sensors (which are fast becoming standard in phones and cameras), which can supplement the motion path computation algorithm.

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#73

Post by whinybastard » Tue, Oct 11, 2011, 10:29 AM UTC

Geee wrote: post #24

It's called blind deconvolution. Blind means that they have to first estimate the original convolution/blur kernel and in the second phase, apply the deconvolution. If there's acceleration sensor on the camera, you can use data from that for the blur kernel. It's nothing new really, but algorithms for it have advanced tremendously. For example, there's some results from 2009 http://www.youtube.com/watch?v=uqMW3OleLM4…

I remember doing some blind source separation for audio when i was at school, that allows you to discriminate multiple voices in noise environment. I wonder what would be the set of output signals in the case of images ... maybe the image illuminated by different sources?

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#74

Post by dpe82 » Tue, Oct 11, 2011, 10:37 AM UTC

elithrar wrote: post #64

wickedchicken wrote: post #35

Earlier quoted context omitted.

One key problem with deconvolution is it's very susceptible to noise. I'm guessing they developed a way to ramp up the coefficients so you see an increase in clarity while keeping the noise below visible levels. So much of image (and audio!) processing is about getting away with noise the person can't detect :) On a side note: does anybody know of workable deconvolution algorithms that vary the kernel over the image?…

> So much of image (and audio!) processing is about getting away with noise the person can't detect :) Adobe's noise processing algorithms in their software are something else, especially in ACR6/Lightroom 3. I moved 'down' from a 5D2 to a Panasonic GF1 as I don't shoot pro anymore, and ISO1600 on this thing with a slightly-off exposure can be pretty noisy. Lightroom cleans it up incredibly well without losing clarit…

It's a very different kind of noise. Artifacts, is what he meant to write. Motion deconvolution done wrong tends to lead to things like ring artifacts and other things that look like the image has been really badly and inaccurately oversharpened.

The basic theory for doing this type of deblurring isn't too bad, but making it easy and automatic becomes a really difficult computer vision-related problem. Adobe has been working on this (and a lot of other pretty cool stuff) for quite a while. It'll be interesting if they ever ship it.

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#75

Post by epo » Tue, Oct 11, 2011, 10:43 AM UTC

georgieporgie wrote: post #41

So, why did the whole video look really fake? It seemed to bob around in a very predictable manner. When the first sharpening took effect, it panned and zoomed exactly in time with the appearance of the second image. I'm not claiming the demo is fake, I'm just wondering why the video looks so strange.

All first-look demos like this are staged/faked whatever, why would you think otherwise?

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#76

Post by atomicdog » Tue, Oct 11, 2011, 10:49 AM UTC

bluedanieru wrote: post #58

DavidSJ wrote: post #44

Earlier quoted context omitted.

Being paid to be rude doesn't make it not rude.

He was paid to be rude to the people who were paying him to be rude? That might not make it not rude, but I can't imagine anything that would come closer.

It was rude to be rude to the people paying him to be rude because it appears to the other members of the audience who were not being paid to be rude that being rude and interrupting the talk is acceptable practice.

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#77

Post by dpe82 » Tue, Oct 11, 2011, 10:50 AM UTC

dpe82 wrote: post #60

mey wrote: post #30

Earlier quoted context omitted.

Does this algorithm lend itself to video? Probably would take a massive cloud of systems to correct any highdef video signal, but it would be impressive for many applications (news broadcast, sports, or any live event, security, or remote robots) Granted to achieve performance on the order of near realtime dsp, it would require an impressive hardware system. Then again, when I can spend the price of a coffee and get…

One of the things I did during my stint at Sony was video stabilization for their desktop nonlinear video editing software. We were hoping to not only stabilize (which is a pretty straightforward thing to do these days) but also use the motion data to inform a deconvolution to clean up motion blurred frames. Alas, my project ran out of time and we ended up licensing a third party stabilizer. But yes, most image proce…

I should clarify: many things like this lend themselves to video, but not directly. As ibuildthings pointed out you have to be very careful becuase for video the human eye is very sensitive to the sharp edge artifacts algorithms like this can produce; much more so than it is to motion blur.

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#78

Post by MichaelApproved » Tue, Oct 11, 2011, 10:53 AM UTC

daimyoyo wrote: post #70

What they should do is partner with a DSLR maker and put this in the firmware of the camera itself. Imagine one button blur correction. That'd be amazing.

I don't think DSLRs have the processing power needed to unblur the images. It took several seconds to unblur a section of an image. It'd probably be faster to upload the image to a cloud processor and have it unblur it for you.

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#79

Post by Geee » Tue, Oct 11, 2011, 10:56 AM UTC

dpe82 wrote: post #77

dpe82 wrote: post #60

Earlier quoted context omitted.

One of the things I did during my stint at Sony was video stabilization for their desktop nonlinear video editing software. We were hoping to not only stabilize (which is a pretty straightforward thing to do these days) but also use the motion data to inform a deconvolution to clean up motion blurred frames. Alas, my project ran out of time and we ended up licensing a third party stabilizer. But yes, most image proce…

I should clarify: many things like this lend themselves to video, but not directly. As ibuildthings pointed out you have to be very careful becuase for video the human eye is very sensitive to the sharp edge artifacts algorithms like this can produce; much more so than it is to motion blur.

Yep, I can imagine continuity problems, flicker etc. could show up in video.

Re: Photoshop 'unblur' leaves MAX audience gasping for air

#80

Post by StavrosK » Tue, Oct 11, 2011, 10:58 AM UTC

georgieporgie wrote: post #41

So, why did the whole video look really fake? It seemed to bob around in a very predictable manner. When the first sharpening took effect, it panned and zoomed exactly in time with the appearance of the second image. I'm not claiming the demo is fake, I'm just wondering why the video looks so strange.

I think it would be unreasonable to claim that it is fake anyway, since relevant research has been public for some time. If there's an amount of trickery involved, it's in the parameter files he loaded (they might be nontrivial/nonautomatic to produce).