correcting out of focus photos

Being very skeptical, I had to try it, but it does sort of work.

dsc6237combined.jpg


Ok, it's not perfect, but it does seem to have to worked quite well. In the shot that was actually out of the focus (rather than an artificial gaussian blur) you can't see my dog's white chin, but it has actually come out in the unblurred .

I can't really see a use a photographer would have for the app though as the image that is produced is a bit dodgy looking.
 
Finally we will now have good evidence of UFOs and the Loch Ness monster.
 
I'm surprised that this never made it to Photoshop:

http://www.youtube.com/watch?v=xxjiQoTp864

Heres a link to the photos used, note the images were blured to give the effect of camera shake, with a known PSF it's fairly simple to un-blur to a decent degree, it's a different thing when you don't know the PSF.

http://blogs.adobe.com/photoshopdotcom/files/2011/10/Plaza.png

A real world image test with unknown PSF.

http://blogs.adobe.com/photoshopdotcom/files/2011/10/sarah-dog.png
 
The cheeky.......

The video gives the impression it was calculating the PSF and there was no indication it was not staged.

Not happy now :(
 
Heres a link to the photos used, note the images were blured to give the effect of camera shake, with a known PSF it's fairly simple to un-blur to a decent degree, it's a different thing when you don't know the PSF.

http://blogs.adobe.com/photoshopdotcom/files/2011/10/Plaza.png

A real world image test with unknown PSF.

http://blogs.adobe.com/photoshopdotcom/files/2011/10/sarah-dog.png

If you're going to call Adobe on being misleading, at least make sure you have your caption correct and that it backs up your assertion

Where those images are taken from: http://blogs.adobe.com/photoshopdotcom/2011/10/behind-all-the-buzz-deblur-sneak-peek.html

Adobe photoshop.com blog said:
Challenges with Deblur

However, there is still quite a bit of development left to do before this feature is ready for prime time. Although some of these early demos will wow audiences, there is a lot more to blur than meets the eye. For instance, there are algorithms that estimate where blurs occur in an image and determine what type they are, and others that then reconstruct the image.

The before image below has a blur caused by camera shake. The after image shows the type of magic that can occur when the right algorithm is applied using Jue’s new prototype.

[first image posted above]

The tricky part is when an image has more than one kind of blur, which occurs in most images. Current deblur technology can’t solve for different blur types occurring in different parts of a single image, or on top of one another. For example, if you photograph a person running and also shake the camera when you press the shutter, the runner will be blurry because he is moving and the whole image might have some blur due to the camera shake. If an image has other issues like the noise you often get from camera phones, or if it was taken in low light, the algorithms might identify the wrong parts of an image as blurry, and thus add artifacts in the deblur process that actually make it look worse.

Strong edges in an image help the technology estimate the type of blur. The image below shows the same algorithm run on the image above without the benefit of strong edges. You see that it fails in this case.

[second image posted above]

[emphasis added]

Nowhere in the blog article those photos were taken from, does it mention an 'unknown PSF' (or even the word 'unknown').

Moreover, of the three images shown in the demo, it was only one that was subjected to synthetic motion blur - a portrait of Adobe CTO, Kevin Lynch

From the same piece, when Adobe updated the blog after it was revealed that the photo of Kevin Lynch had been synthetically blurred.

Adobe photoshop.com blog said:
UPDATE: For those who are curious – some additional background on the images used during the recent MAX demo of our “deblur” technology. The first two images we showed – the crowd scene and the image of the poster, were examples of motion blur from camera shake. The image of Kevin Lynch was synthetically blurred from a sharp image taken from the web. What do we mean by synthetic blur? A synthetic blur was created by extracting the camera shake information from another real blurry image and applying it to the Kevin Lynch image to create a realistic simulation. This kind of blur is created with our research tool. Because the camera shake data is real, it is much more complicated than anything we can simulate using Photoshop’s blur capabilities. When this new image was loaded as a JPEG into the deblur plug-in, the software has no idea it was synthetically generated. This is common practice in research and we used the Kevin example because we wanted it to be entertaining and relevant to the audience – Kevin being the star of the Adobe MAX conference!

[emphasis added]

The first of the two images you posted was the 'crowd scene' in the demo, which was real blur from a real camera.
 
Last edited:
If you're going to call Adobe on being misleading, at least make sure you have your caption correct and that it backs up your assertion

Where those images are taken from: http://blogs.adobe.com/photoshopdotcom/2011/10/behind-all-the-buzz-deblur-sneak-peek.html



[emphasis added]

Nowhere in the blog article those photos were taken from, does it mention an 'unknown PSF' (or even the word 'unknown').

Moreover, of the three images shown in the demo, it was only one that was subjected to synthetic motion blur - a portrait of Adobe CTO, Kevin Lynch

From the same piece, when Adobe updated the blog after it was revealed that the photo of Kevin Lynch had been synthetically blurred.



[emphasis added]

The first of the two images you posted was the 'crowd scene' in the demo, which was real blur from a real camera.

Sadly not quite, the shopping mall photo has already been spotted and identified as not suffering camera shake due to a short exposure being used, it seems the blur was added later.
 
Back
Top