Beta

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Adobe Demos Photo Unblurring At MAX 2011

timothy posted more than 2 years ago | from the 174-days-early dept.

Graphics 251

karthikmns writes with word of an amazing demo presented last week at Adobe's annual MAX convention. You'll have to watch the video, but the enthusiastic crowd reaction seems genuine (or at least justified), even in an audience full of Photoshop enthusiasts, as photographs are algorithmically deblurred. (Maybe in the future, cameras will keep records of their own motion in metadata to assist such software efforts, rather than relying on in-built anti-shake software.) No word about when this will turn up for consumers in anything besides demo form, but I suspect similar software's already in use at Ft. Meade and Langley.

cancel ×

251 comments

Sorry! There are no comments related to the filter you selected.

If the video could be unblurred.. (5, Funny)

Bongoots (795869) | more than 2 years ago | (#37679452)

I'd be able to see the demo!

Re:If the video could be unblurred.. (1)

Gaygirlie (1657131) | more than 2 years ago | (#37679666)

I'd be able to see the demo!

Indeed, the video is quite poor quality. Rather disappointing :/ I did choose the 720p and fullscreen to see if I could see the difference better, but it doesn't really help much.

Re:If the video could be unblurred.. (2)

93 Escort Wagon (326346) | more than 2 years ago | (#37680004)

Indeed, the video is quite poor quality. Rather disappointing :/ I did choose the 720p and fullscreen to see if I could see the difference better, but it doesn't really help much.

Yeah, it's too bad there's not an easy way for YouTube to display the effective pixel density of a video - that one would be maybe 60p.

That video was another fine example of the megapixel myth.

Re:If the video could be unblurred.. (3, Interesting)

tepples (727027) | more than 2 years ago | (#37680182)

Yeah, it's too bad there's not an easy way for YouTube to display the effective pixel density of a video

That would take three steps: 1. find edges; 2. pick some edges and do Fourier transforms; and 3. figure out how wide the passband is. YouTube could do that at encode time, but it'd have to be done on keyframes throughout a video, or videos with multiple resolutions edited together (e.g. HD video made with SD file footage) would fool it.

Re:If the video could be unblurred.. (4, Funny)

orangesquid (79734) | more than 2 years ago | (#37680146)

Hmm...
  "drawing a laoud applause" "not yet made it clear weather" "will be shipping quite a few number of units"

laoud? weather? few number of units?

I tried saying "Enhance!" a few times, but that didn't un-blur the article's spelling/grammar/word choice+usage. ;)

Re:If the video could be unblurred.. (1)

jellomizer (103300) | more than 2 years ago | (#37680142)

I feel seasick from the demo. Perhaps they should invest in a steady cam... If that is too expensive how about a tripod!

Interpolated missing data is still just a fiction (0)

elrous0 (869638) | more than 2 years ago | (#37679458)

I suspect similar software's already in use at Ft. Meade and Langley.

I certainly hope not.

This will make things LOOK pretty. It won't make missing data suddenly appear. At best it will make something ugly LOOK a little better. But that's just a computer-generated illusion, not a reflection of reality.

Re:Interpolated missing data is still just a ficti (3, Insightful)

SteveX (5640) | more than 2 years ago | (#37679518)

Did you watch the video? It makes unreadable text readable. That falls into the category of making missing data suddenly appear.

Re:Interpolated missing data is still just a ficti (5, Insightful)

mfwitten (1906728) | more than 2 years ago | (#37679612)

I think it would be better to say that [most of] the data are already present; the data just happen to be initially in an unwanted form.

Re:Interpolated missing data is still just a ficti (0)

Anonymous Coward | more than 2 years ago | (#37679808)

Yea. It's the "I'm just going to load some parameters" that is the "interesting" part.

Re:Interpolated missing data is still just a ficti (5, Insightful)

Artraze (600366) | more than 2 years ago | (#37679898)

No, and really no to everyone else. This is making _obfuscated_ data suddenly because visible.

It characterizes the the motion of the camera from the blur then reverses it: essentially an image stabilization algorithm. It's like making voices audible over loud music by figuring out what the song is and subtracting it from the mix.

It's cool, but not magic. They aren't even pretending to add in missing data like a CSI zoom. Nor does it even seem to take care of simple out of focus situations. So let's not get too excited, well, unless you've got a cheap/slow camera.

Re:Interpolated missing data is still just a ficti (1)

adonoman (624929) | more than 2 years ago | (#37680016)

This could be usefull in low-light situations where you don't have a tripod, but yeah, it's not adding in any new information, it's just better organizing the data that's been captured. Also, I doubt it would be able to do anything for a specific subject that was moving during the shot, rather than the camera.

Re:Interpolated missing data is still just a ficti (1)

hcs_$reboot (1536101) | more than 2 years ago | (#37679992)

It makes unreadable text readable. That falls into the category of making missing data suddenly appear.

I don't know the details of that feature, but wouldn't be surprised that the "repair" mode comes into two flavors: automatic and manual
- the automatic mode would try to guess from embedded data like Exif and the picture itself what it is supposed to show.
- the manual mode would ask the user if the part to be repaired is text, landscape, face...

In the case of a text, the algorithm could either compare each letter with the ones it knows (from fonts), or words from a dictionary - the user would select a language first.
I don't believe in miracles.

Re:Interpolated missing data is still just a ficti (1)

shish (588640) | more than 2 years ago | (#37679570)

But that's just a computer-generated illusion, not a reflection of reality.

I wouldn't go that far, I'd say it's more like making an educated guess -- and while it's true that a guess is a guess and you should never take it for fact, a guessing tool that is consistently 95% accurate is still incredibly useful, even if just to narrow down the places that humans should then go and investigate by hand.

Re:Interpolated missing data is still just a ficti (1)

Dunbal (464142) | more than 2 years ago | (#37679580)

At best it will make something ugly LOOK a little better.

Or in the case of cosmetics ads, make something that looks good look a little uglier.

Re:Interpolated missing data is still just a ficti (5, Funny)

Skarecrow77 (1714214) | more than 2 years ago | (#37679584)

How hard can it be, I mean, they've been doing it in movies since at least the 80s. Hell even the $500 dell desktop on CSI:miami can do it.

"we've got a convenience store video feed of the getaway car, the camera was recording in 480i from 300 yards away"
"can you sharpen it up a little?"
"sure. one moment... ok got it. License plate is california JGL-711. Ok just a bit more... yeah, looks like registration expires march 2012. Wait, let me clean it up some more, yeah it looks like there's a small identifying scratch on the trunk lid about a half inch long shaped like a boomerang. Oh wait, this is the new version of the software, let me zoom in a bit further, yeah I'm pretty sure I'm seeing loose skin cells on the edge of the trunk lid, maybe our missing person is in the trunk!"
"good work, now where's my sunglasses?"

yeeeeeeeeeeeeeeeeeeeeeeeeeeeaaaaahhhh!

Re:Interpolated missing data is still just a ficti (1)

NatasRevol (731260) | more than 2 years ago | (#37679812)

You totally missed the clue. Boomerang scratch? Going under the I-37 bridge as the crossing arm lowers. We know EXACTLY where they are!

Re:Interpolated missing data is still just a ficti (0)

Anonymous Coward | more than 2 years ago | (#37679836)

Too bad he didn't have the even newer version of the software or he'd be zoomed in on the DNA in those skin cells and running it against the all-knowing database.

Re:Interpolated missing data is still just a ficti (1)

kungfuj35u5 (1331351) | more than 2 years ago | (#37680136)

The data in csi is not obfuscated it's missing. This algorithm reverses motion blur it does not bump up any resolution, these are two completely different things.

Re:Interpolated missing data is still just a ficti (2)

pla (258480) | more than 2 years ago | (#37679630)

This will make things LOOK pretty. It won't make missing data suddenly appear. At best it will make something ugly LOOK a little better. But that's just a computer-generated illusion, not a reflection of reality.

Yes and no - No, you can't magically create information not present in the original image.

You can, however, calculate the most likely "true" value for any point on the image, given a sufficiently accurate model of the distortion present (in this case, an incorrect focal plane). Whether or not that allows any functionally useful interpolation, you can still get a pretty good ID from a few dozen pixels squared, if sufficiently clear (think Slashdot's Gates-Borg icon).

Re:Interpolated missing data is still just a ficti (1)

An dochasac (591582) | more than 2 years ago | (#37679900)

You're also exchanging some pixel depth (color/greyscale levels) and information about the point spread function for spacial resolution. It looks like magic but it's a very old technique. I did similar in the mid 1990s. Capturing camera motion (accelerometer) during the photograph would be useful here since it helps you calculate the point spread function. To poster who worried about the memory this would require, we're talking about three long ints or 6 bytes for the X, Y and Z vectors. Since we're below $1/gigabyte for flash, you're talking about ~0.0000006 cents per photo. So, no I wouldn't worry about it. It would be ideal for iPhones and Androids which already have an accelerometer and the small image sensor means low shutter speeds which means lots of motion blur in dim light.

Re:Interpolated missing data is still just a ficti (2)

drobety (2429764) | more than 2 years ago | (#37679684)

Interpolated missing data is still just a fiction

Yes it is. However, in the present case they reuse *existing* data. Requires a lot of processing, but this is not an artifice, they really use computing power to first determine the camera movement, and from this information, they can re-compute each pixel by removing as much as they can the blur resulting from the camera movement, which gives much better results than using a straightforward generic edge enhancement.

Re:Interpolated missing data is still just a ficti (1)

DreadPiratePizz (803402) | more than 2 years ago | (#37679722)

Well if you watch the demo, the presenter makes unreadable text on a poster readable after the filter is applied.

Re:Interpolated missing data is still just a ficti (1)

Anonymous Coward | more than 2 years ago | (#37679726)

But the point is that in a normal blur situation, very little data is missing (unless the degree of blur is catastrophic). A simple model for blurring is that it happens because the camera was in motion relative to the subject when the photo was taken. All the data is still there, it's just smeared into the wrong pixels due to the motion. If you are able to guess the direction and speed of the motion of the camera at the time the photo was taken, you can put it back into the right place and reconstruct the photo.

Now, there are some obvious problems. If some pixels are saturated, any data that was smeared into them will be permanently lost. Things near the edges of the photo may not be reconstructable. And in photos of very close-by objects, parallax may hurt results, especially near the edges of objects (this seems like a tiny effect to me, but I'm not an expert). But the point remains that almost no data is missing.

The algorithm does not claim to work on photos that are "blurry" because they were taken at too low a resolution.

Re:Interpolated missing data is still just a ficti (1)

EdZ (755139) | more than 2 years ago | (#37679766)

They show what they call a 'blur kernal' the calculation of which takes up the majority of the processing time. I'm guessing they use that to perform a 2D deconvolution on the image (there is software that already does this). The interesting part is how they calculate the kernal.

Re:Interpolated missing data is still just a ficti (1)

beelsebob (529313) | more than 2 years ago | (#37679786)

Actually, it could quite reasonably make data that was there, but obscured in such a way that a human eye can't make it out, suddenly appear. The demo shows an example of taking a photo of a poster that's blurred beyond reading, and getting perfectly crisp sharp text back.

A fiction our brain naturally employs anyway. (2, Insightful)

Anonymous Coward | more than 2 years ago | (#37679788)

It's not entirely about whether a digitally de-blurred image is more accurate than an inherently sharp image.

It's also about whether the sensory impression made on a human by a digitally de-blurred image is a more accurate a model of the reality than the sensory impressions made by a blurred image. Of course your occipital lobes do plenty of interpolating of their own, so surely the question becomes which system (digital or organic) produces the more reliable interpolations.

Maybe if a person studied the blurred picture long enough they could have reconstructed that telephone number, hard to say from the mediocre quality video of a small display window.

I certainly wouldn't discount software being able to outperform even a trained person in sufficiently narrow fields, and I doubt you would either.

Re:Interpolated missing data is still just a ficti (0)

Anonymous Coward | more than 2 years ago | (#37679798)

Here's a datapoint for you - I can take a barcode (which is 108 pixels wide) and image it on a webcam, out of focus, at 90 pixels wide, and my software can correctly output the 13 digits that the barcode represents.

This doesn't break any information theoretic laws, but it does give me the intuition to stop before claiming that all clever image processing is just "interpolation" and that data is "missing".

Re:Interpolated missing data is still just a ficti (1)

squizzar (1031726) | more than 2 years ago | (#37680050)

Those are digits in the 0-10 range right? So you have a key space of 10^13, which is 0x918 4e72 a000, or 44 bits. So the 90 pixels could easily be more than enough. My information theory is a bit wobbly, but I think that works. Unless your encoding is horribly inefficient you've got plenty of samples there. Also if you're being smart you could probably read the barcode diagonally to gain some extra information.

Re:Interpolated missing data is still just a ficti (1)

mikael (484) | more than 2 years ago | (#37680208)

Each pixel element consists of at least three eight or sixteen bit values, so that's at least sixteen million values per pixel. Assuming monchrome, thats 256 or 65536 values per pixel.

I did some experiments with those digital photograph postcard printing booths and a scanner. You could easily create an image, print it out, and scan it back in again to recover a few hundred kilobytes.

The trick is to create a couple of horizontal and vertical bands of coordinates encoded in binary. Then you can see what the recoverable resolution is.

Re:Interpolated missing data is still just a ficti (0)

Anonymous Coward | more than 2 years ago | (#37679818)

At best it will make something ugly LOOK a little better. But that's just a computer-generated illusion, not a reflection of reality.

So, it's perfect for pr0n. Who cares if it's fiction, isn't that a good thing?

Re:Interpolated missing data is still just a ficti (1)

Max Romantschuk (132276) | more than 2 years ago | (#37679820)

This will make things LOOK pretty. It won't make missing data suddenly appear. At best it will make something ugly LOOK a little better. But that's just a computer-generated illusion, not a reflection of reality.

It's not that simple. What's likely happening here is two things: First, the image is analysed and the probable motion trajectory of the camera while the shutter was open is calculated. Then a convolutive algorithm is used to reverse the motion. This is entirely doable. The information is there in the image, the trick is just how to extract it.

A gaussian blur, for example, can be applied "backwards" and the sharp original recovered, if you know the parameters used. So if Adobe's motion trajectory analysis is good enough the results could be quite close to the truth.

I don't know the math well enough myself to prove that I'm correct, but I'm sure someone better educated in the area could confirm or deny my claims?

Re:Interpolated missing data is still just a ficti (2)

artor3 (1344997) | more than 2 years ago | (#37679828)

The data here isn't missing, just obfuscated. A common lab for EEs is to unblur a picture in this way. It's much harder in real life, where you need to find what they're calling the blur kernel, but there's no reason for it to be impossible.

Re:Interpolated missing data is still just a ficti (0)

Anonymous Coward | more than 2 years ago | (#37679876)

I work in image processing, and think this may be useful.

At the risk of a buzzkill, this is nothing more than deconvolution. This is used in science and behind-the-scenes in all sorts of industries to correct for the point-spread function (PSF) of a given imperfect system in the general field of 2-D digital signal processing, most often applied in imaging.

The innovation is that they have come up with an algorithm to analyze a given photo (or region) in reasonable amounts of time to find or approximate the PSF from blurring. After this is done, applying it (deconvolving) is a fast operation. Note that he calls what gets extracted a "blur kernel" and then goes on to explicitly call it a PSF as an aside in the presentation.

What this is NOT is magic. The information is there, it's just not sharp due to blurring; what should be consolidated in one pixel is now spread over a region. It won't fix every photo, won't bring back lost information, and isn't making data appear out of thin air. With those caveats, however, it is a powerful technique.

Re:Interpolated missing data is still just a ficti (2)

smash (1351) | more than 2 years ago | (#37679896)

Not really. It analyses the photo to determine the movement of the camera at time of shooting, and un-does that movement. Given enough colour resolution, i'm pretty confident that useful detail retrieval could be achieved - not just some artificial generated details to make the photo "look good".

This does work and isn't an illusion. (2)

pavon (30274) | more than 2 years ago | (#37679918)

We have done this in my image processing class. It isn't CSI bullshit.

It won't make missing data suddenly appear.

The thing is that the data isn't missing, it is just distributed throughout the image. For example consider an unfocused camera. Instead of each point in the image mapping to a single point in the image, it results in a gaussian centered at that point, and these are all summed together. In signal processing terms, you can think of the blurred image as being the convolution of the desired image and a gaussian function (plus some noise):
xb = x # g + n
Take the Fourier transform, an this becomes a simple multiplication.
Xb = X * G + N
Divide it out, and invert the transform and you get the original image (plus noise):
xEst = X + n#(1/g)

The same can be done with motion blur, except now G is is a curve through space, not a gaussian. The hard part is knowing exactly how the image was blurred (what path it followed for motion blur, or the optic properties for unfocused images). I don't know what they are doing to discover the blur kernel, but it is impressive.

The other hard part is that this procedure can really amplify high-frequency noise, (consider dividing the 1/G; the tail of the gaussian is close to zero, which makes the reciprocal very large), and JPEG artifacts in particular are hell to deal with. There are ways to minimize this problem (for example, optimal Weiner filters), but you have to have a fairly high-quality image to begin with.

If you want to learn more the key terms to search for is image deblurring with deconvolution.

Re:Interpolated missing data is still just a ficti (1)

Kjella (173770) | more than 2 years ago | (#37679938)

This will make things LOOK pretty. It won't make missing data suddenly appear. At best it will make something ugly LOOK a little better. But that's just a computer-generated illusion, not a reflection of reality.

Not really. If I take a picture of a sign and my hand is shaking as I take the picture, you already know it's a fixed, flat surface. If you can algorithmically find exactly how my hand was shaking and so clear up the image, that's not an illusion. Consider it more like that even in the short shutter time you have many images superimposed on each other, this aligns them so the picture becomes clearer. It won't work for the generic case but for a certain class of pictures this is close to magic.

Re:Interpolated missing data is still just a ficti (1)

kimvette (919543) | more than 2 years ago | (#37680114)

This will make things LOOK pretty. It won't make missing data suddenly appear. At best it will make something ugly LOOK a little better. But that's just a computer-generated illusion, not a reflection of reality.

That's not true; the data is there. This is not for OOF (out of focus) photos due to focus error (so if you have a "bad copy" of a lens, or you didn't micro-adjust your lens, or if your lens is decentered, or you simply blew it on the shot it won't help), but for motion blur. All of the data is there but exposed multiple times as the subject moves. Topaz Labs has had a plugin for this a while and it works pretty well.

In the case of focus errors, you're right; the data isn't really there in a way to help this algorithm work.

You gotta hand it to them (1)

AdamJS (2466928) | more than 2 years ago | (#37679506)

It's a pretty sharp idea.

Re:You gotta hand it to them (0)

Anonymous Coward | more than 2 years ago | (#37679748)

Agreed. I am glad they focused their efforts on a useful technology such as this.

Re:You gotta hand it to them (1)

Traciatim (1856872) | more than 2 years ago | (#37680042)

I have to disagree. I only wonder how Aperture science will use this against us^W^W to better humanity.

PC Weenies Cartoon Take (1)

khr (708262) | more than 2 years ago | (#37679508)

Here's the PC Weenies [pcweenies.com] cartoon about this one...

Zoom.. (0)

Anonymous Coward | more than 2 years ago | (#37679532)

Zoom in.. Zoom in.. ENHANCE!

Re:Zoom.. (1)

0100010001010011 (652467) | more than 2 years ago | (#37679826)

Just print the damn thing!

the end. (1)

Dark Lord of Ohio (2459854) | more than 2 years ago | (#37679536)

simply the end of photography. bleh.

Re:the end. (2)

Bobfrankly1 (1043848) | more than 2 years ago | (#37679572)

simply the end of photography. bleh.

If you think photography is simply about getting an un-blurry image, you know nothing of photography.

Re:the end. (1)

hedwards (940851) | more than 2 years ago | (#37679654)

Assuming it works, which I highly doubt it ever will work properly, this could flood the market with those photos that were compositionally perfect, just just out of focus. That being said, I'm not holding my breath.

Re:the end. (3, Informative)

eobanb (823187) | more than 2 years ago | (#37679762)

This does NOT fix images that are out of focus. This fixes motion blur. The two are entirely unrelated.

Re:the end. (1)

Dark Lord of Ohio (2459854) | more than 2 years ago | (#37679776)

no, it's not just about getting an unblurry image. But to get one you have to know a little how to get such picture. thats why pictures which are not digitally processed with Photoshop (or Gimp, whatever) are the best. Thats my opinion, maybe yours different because you shot many blurred photos, then yeah.. why not. Have fun.

Re:the end. (1)

Pope (17780) | more than 2 years ago | (#37679936)

Simultaneously ignorant, and elitist. Congratulations, here's your (organic, fair trade) no-tea.

Don't Hold Your Breath (4, Interesting)

cranky_slacker (815016) | more than 2 years ago | (#37679554)

This demo came during the 'Sneak Peaks' portion of the conference. The technology may never make it to market.

That being said, I was at MAX and the demo was as amazing as it looks. Essentially, the software determines the motion/jitter of the camera at the time the photo was taken (i.e. figures out what caused the blur) and then undoes it. I can't imagine why they wouldn't include this in future version of photoshop.

Re:Don't Hold Your Breath (2)

dreemernj (859414) | more than 2 years ago | (#37679780)

I can't watch the vid because of an incredibly slow connection, but I was guessing this is only for motion blur and not from, say, the camera being out of focus. Is that correct?

I can imagine people saying its impossible if its about unblurring out of focus pictures, but for motion blur, once the path is extrapolated, it seems like there should be some sort of computer magic that backtracks along the path to build up an impression of what the original image was.

Re:Don't Hold Your Breath (1)

Anonymous Coward | more than 2 years ago | (#37679940)

I can imagine people saying its impossible if its about unblurring out of focus pictures

Maybe people would say it but I have no idea why they would. Focus blur is a purely linear phenomenon and completely reversible in software (assuming you have an approximation of the blur kernel, which is not hard to acquire)

Re:Don't Hold Your Breath (1)

cranky_slacker (815016) | more than 2 years ago | (#37680030)

yeah, it was for motion blur.

Already in use in Hollwyood (1)

tverbeek (457094) | more than 2 years ago | (#37679556)

A staged demo using images that lend themselves to the kind of interpolated guesswork that this uses is one thing. Making it work with real-world forensics is quite another.

Re:Already in use in Hollwyood (1)

cranky_slacker (815016) | more than 2 years ago | (#37679602)

I don't think that forensics was the intention. I think it's more targeted to people who can't hold a camera steady.

Re:Already in use in Hollwyood (1)

internerdj (1319281) | more than 2 years ago | (#37679724)

I think they make a hardware solution for this called a tripod...

Re:Already in use in Hollwyood (2)

nedlohs (1335013) | more than 2 years ago | (#37679884)

Including that makes a cell phone camera just a little larger than desirable, and makes taking a snapshot take just a fraction more time.

Re:Already in use in Hollwyood (0)

Anonymous Coward | more than 2 years ago | (#37679886)

In anything less then bright sunlight it's legitimately difficult to handhold longer focal lengths.

At night or in a bar it's hard to handhold any focal length.

IS helps, higher usable ISOs help, I'd have to try this unblurring software to decide if it's any good.

Re:Already in use in Hollwyood (1)

doggo (34827) | more than 2 years ago | (#37679670)

Whatever, Eeyore. Images that lend themselves to the kind of interpolated guesswork that this uses are blurry ones. Y'know, the kind you get in the real world?

Re:Already in use in Hollwyood (0)

Anonymous Coward | more than 2 years ago | (#37679986)

There is a reason photos that have been digitally altered in any way are instantly inadmissible in court.

Yeah (1)

Dunbal (464142) | more than 2 years ago | (#37679562)

Maybe in the future, cameras will keep records of their own motion in metadata to assist such software efforts

Because we all could use just a little more file size bloat. After all, memory is cheap, right?

Re:Yeah (2)

canajin56 (660655) | more than 2 years ago | (#37679682)

Yes indeed, we can't add a few bytes of accelerometer data to a 10 megapixel image, that would make those images too large!

Re:Yeah (0)

Anonymous Coward | more than 2 years ago | (#37679688)

That ship sailed a long time ago, RAW files are big and getting bigger, Nikon is talking about a 36 megapixel sensor.

Re:Yeah (2)

Jeng (926980) | more than 2 years ago | (#37679924)

If people cared about file size bloat they wouldn't be purchasing the most megapixels possible.

After all, memory is cheap.

Re:Yeah (1)

MikeBabcock (65886) | more than 2 years ago | (#37679954)

I considered trying to do this once with a photo cap on Android ... store the accelerometer data in real time as the shutter was clicked.

Wasn't helpful without the algorithm they're using though.

deconvolution? (1)

vsage3 (718267) | more than 2 years ago | (#37679582)

It doesn't sound that much harder of a problem to solve than what I learned in EE undergrad about deconvolution. Divide the Fourier transform of the blurred image by the fourier transform of the "motion kernel" as they call it to get the sharpened image. I routinely use a similar method in the lab to correct for visual aberrations in my diffraction spot imaging equipment, but there the problem is much easier as the motion function is exactly traced out by the diffraction spots.

Perhaps getting the "motion kernel" is harder than I suspect it to be in a real life scenario, though.

Re:deconvolution? (1)

TeknoHog (164938) | more than 2 years ago | (#37679770)

Yes, this is basically deconvolution. If you don't know the convolution kernel, there are statistical methods to find the most likely solution for a given blurry image. I heard about these techniques about 10 years ago via prof. Steve Gull, one of the people behind MaxEnt [maxent.co.uk] .

Re:deconvolution? (1)

dreemernj (859414) | more than 2 years ago | (#37679822)

It sounds similar to what you are familiar with. I would bet the motion kernel is pretty tricky to get right. And, of course, bundling it into a user friendly piece of software and shipping it add to the complexity of making it as well. I wouldn't be surprised if someone made some sort of GIMP add on that did something along the lines of this years ago but that hasn't been developed to the same level Adobe would develop it (if they release it) and that hasn't attained the level of attention since there is no big industry name attached to it.

"I'm just going to load some parameters..." (2)

bradgoodman (964302) | more than 2 years ago | (#37679588)

There seemed to be a bit of "smoke and mirrors" behind some of these demos. He kept "loading some parameters" for each of the demos. Granted, the video was so blurry you couldn't really see the results.

I'll think I'll reserve judgement though until I can see it "for real".

Who were the annoying guys off to the side that loved hearing themselves talk? Really kind of ruined the momentum. This isn't MST3k

Re:"I'm just going to load some parameters..." (1)

EmagGeek (574360) | more than 2 years ago | (#37679650)

This caught my attention immediately, and I think you are right. He loaded different parameters for each photo, leading me to believe that there was a significant amount of pre-processing done even before the "analysis" step he demonstrated.

Re:"I'm just going to load some parameters..." (1)

cranky_slacker (815016) | more than 2 years ago | (#37679720)

The results were quite good. As far as the preloaded parameters goes, my impression was that that was done to keep the presentation moving. Obviously I don't know for sure, but that's how it looked. There were quite a few knobs and sliders in the UI.

Re:"I'm just going to load some parameters..." (1)

Ironix (165274) | more than 2 years ago | (#37679778)

As he stated at the beginning of the demo, the plugin was still in development and there appeared to be a multitude of sliders and settings to set in order to get any particular photo to come out 'just right'. I'm assuming he had limited stage time and felt that saving all those settings to be loaded on an as needed basis would save time.

Otherwise, would you have been more content to sit there and watch him fiddle with sliders and settings for 5-10 minutes per photo in order to achieve the results he produced with saved settings? In fact, he explicitly stated that he was loading some presets.

Additionally, if you look at the file size column when he loads the pre-defined parameters, they are single-didgit file sizes, Most likely 1 KB each.

Re:"I'm just going to load some parameters..." (1)

bradgoodman (964302) | more than 2 years ago | (#37679882)

Right - but my question would be - how long would it reasonably take to "adjust the parameters" to get a photo correct. A minute? Any hour? A day? A week? Seriously. -BKG

Re:"I'm just going to load some parameters..." (1)

Ironix (165274) | more than 2 years ago | (#37679968)

It was insinuated that continued development would reduce the number of parameters to adjust. If you program, don't you ever put in a bunch of extra settings that a user would never touch, but you would like to play with until you get things just right?

Re:"I'm just going to load some parameters..." (1)

Anonymous Coward | more than 2 years ago | (#37680026)

1KB is sufficient to define a (small) blur kernel (PSF) with high accuracy. I don't claim the demo was faked (indeed, I think it's perfectly reasonable given the current trajectory of image-processing algorithms), but it is plausible that the blur kernels were precomputed or known in advance and loaded into the filter.

Re:"I'm just going to load some parameters..." (0)

Anonymous Coward | more than 2 years ago | (#37680164)

Who were the annoying guys off to the side that loved hearing themselves talk? Really kind of ruined the momentum. This isn't MST3k

One of them was Rainn Wilson who plays Dwight on "The Office." He was there as a celebrity guest so he was probably doing what he was hired to do. I think the other guy was the MC for the overall event.

Japanese porn enthisuasts around the world.. (0)

Anonymous Coward | more than 2 years ago | (#37679622)

..just came, simultaniously

Re:Japanese porn enthisuasts around the world.. (1)

morgaen (1896818) | more than 2 years ago | (#37679922)

You can't put a price on efficient public transport.

Deconvolution (0)

Anonymous Coward | more than 2 years ago | (#37679632)

The process is called deconvolution, but it does not work always that great...
Here is a freeware http://www.zen147963.zen.co.uk/

Ft. Meade? (1)

Eevee (535658) | more than 2 years ago | (#37679664)

Surely you mean Ft. Belvoir [nga.mil] .

Re:Ft. Meade? (1)

acoster (812556) | more than 2 years ago | (#37679744)

Ft Meade is where the NSA headquarters are located.

Re:Ft. Meade? (1)

idontgno (624372) | more than 2 years ago | (#37680200)

Yes, NSA, where they do electronic, communications, and computer intelligence processing. And only that.

As opposed to NGA, or NRO, both of which are involved with imagery intel.

Try to get your agencies right.

Motion Blur not Focus Blur (1)

Anonymous Coward | more than 2 years ago | (#37679678)

Its important to realize that this technology removes motion blur but does nothing about an out of focus image. Fixing motion blur is (clearly) entirely feasible by figuring out how light that was supposed to fall on one pixel was spread out across multiple pixels based on the motion of the camera and then removing that extra light data from the wrong pixels and putting it into the correct pixels. I don't know if this is how they do it but it is how I imagine it would be done, and it is amazing that they can get the results after a couple clicks.

Re:Motion Blur not Focus Blur (1)

EmagGeek (574360) | more than 2 years ago | (#37679754)

Did you happen to notice the "here, let me just load some parameters" step for each photo?

That is the curious bit, and while it may have been just a couple of clicks for the demo, I imagine there was a significant amount of work put into generating those 'parameters'.

For all we know, the "parameters" were just the unblurred versions of the photographs.

Oblig. (0)

Anonymous Coward | more than 2 years ago | (#37679692)

He didn't yell ENHANCE!

How's Yer Sheep? (1)

theshowmecanuck (703852) | more than 2 years ago | (#37679694)

Enhance 224 to 176. Enhance, stop. Move in, stop. Pull out, track right, stop. Center in, pull back. Stop. Track 45 right. Stop. Center and stop. Enhance 34 to 36. Pan right and pull back. Stop. Enhance 34 to 46. Pull back. Wait a minute, go right, stop. Enhance 57 to 19. Track 45 left. Stop. Enhance 15 to 23. Give me a hard copy right there.

Re:How's Yer Sheep? (1)

jkflying (2190798) | more than 2 years ago | (#37679994)

Origami unicorns dream of electric sheep.

Japanese Porn? (1)

Capeman (589717) | more than 2 years ago | (#37679714)

I think they'll use this technology for sure to unblur the movies.

Re:Japanese Porn? (1)

imakemusic (1164993) | more than 2 years ago | (#37680116)

Haha yeah!

Except that you clearly haven't watched the video or understood the process as it doesn't work like that.

Photogs who know what they're doing... (1)

EmagGeek (574360) | more than 2 years ago | (#37679790)

... will never ever need this feature.

It is de-convolution (0)

Anonymous Coward | more than 2 years ago | (#37679806)

http://people.csail.mit.edu/billf/papers/deblur_fergus.pdf

Deconvolution (2)

vossman77 (300689) | more than 2 years ago | (#37679854)

We've known about deconvolution [wikipedia.org] forever, the trick figuring out the path of the camera to generate the kernel for the deconvolution. In the TFV, he says we use the custom parameter file (that they probably spent months tweaking for each image), lots of computing power and TADA! unblurred image.

Microsoft had something similar a few year ago, where you have a blurred image and a second underexposed image to do the same thing. see paper here [microsoft.com] and examples here [cuhk.edu.hk]

Not De-Blur (1)

GameboyRMH (1153867) | more than 2 years ago | (#37679862)

More like de-streak. This isn't CSI technology come to real life. If you take a picture while moving the camera it will basically retrace the camera's movement to make a better picture of it.

How would this help fixed cameras? (1)

jpvlsmv (583001) | more than 2 years ago | (#37679906)

In the case of fixed-base (like security) cameras, there is very little camera shake that would blur the image. So tracking the motion of the camera (via 3-axis accelerometer for example) wouldn't help.

Unless you can compute separate motion vectors for each element in the image (think people walking in different directions, each face to deblur would have a different motion vector) this would not seem to improve the performance.

And, of course, the choice of motion vectors would have a huge impact on the reconstructed image. It could easily turn an identifying scar from "across" the cheek to "down" the cheek. I would hope the criminal justice system will have trouble proving anything based on photoshopped evidence.

--Joe

One step closer to... (1)

owlnation (858981) | more than 2 years ago | (#37679914)

... the "enhance!" command. Yay!

Microsoft did it one year ago (2, Informative)

kiwix (1810960) | more than 2 years ago | (#37680002)

Microsoft did a similar demonstration one year ago [slashdot.org] .

Enhance (1)

nerdpecks (2482330) | more than 2 years ago | (#37680094)

Enhance....enhance...enhance...enhance...enhance

Challenge! (1)

Jason Levine (196982) | more than 2 years ago | (#37680204)

I hereby challenge them. Their software versus my fast moving kids who often show up in photos as blurs. I think kids have built in sensors to let them know precisely when a camera is going off, thus enabling them to move at the exact moment to blur and/or ruin the photo.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?
or Connect with...

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>