Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Adobe Photoshop's 'super resolution' made my jaw hit the floor

petapixel.com

Post reply on HN
Print view View original

61–70 of 171 posts

Re: Adobe Photoshop's 'super resolution' made my jaw hit the floor

#61

Post by rozab »

roughly wrote: post #30
ISL wrote: post #6

As a metrologist (and photographer), the difficulty with these techniques is that they can over-represent the information contained within an image; they present an image of what was "probably" there, rather than representing what was. These aren't so different from our own brains, which remember what we thought we saw, rather than the light that reached our retinas. These methods are already in extensive use (most s…

I think this point is worth pushing on a bit harder, which is to say that the "additional details" in the picture are guesses by the software, not actual additional details. The data present in the picture is fixed, the software uses that data to build educated guesses on what was actually there. If the photo doesn't contain enough data to actually determine what a given piece of text in the image says, the software…

In some use cases, like OCR, the accuracy of these guesses can be established in a scientific way. And it tends to be very good.

Re: Adobe Photoshop's 'super resolution' made my jaw hit the floor

#62

Post by nwienert »

hojjat12000 wrote: post #47
nwienert wrote: post #37

Earlier quoted context omitted.

No there certainly is a chance for ML to improve here. Let’s take the classic example of enhancing a blurry photo to get a license plate. Humans may not be able to see much in the blur, but an AI trained on many different highly down-res’d images could at least give you plausible outcomes using far less data than a human brain would be able to say anything with confidence. You wouldn’t hold it up as the absolute trut…

Actually the opposite. These algorithms are more susceptible to noise, they may generate sharp perfect license plate numbers (that are totally fabricated and completely wrong) from a blurry image. But by no means should you even consider the results to have hints of truth. GAN produces totally different results if you slightly change the input. So, as others are also saying, these "enhances" are great for decoration…

No. If their training set isn’t too far off what you use it for, it is valid. Just because it’s not guaranteed, doesn’t mean it’s not more accurate than hitting sharpen and squinting.

You’re fighting against “would it be reliable” but that isn’t the claim.

The claim is could it be better than human, and the answer is yes, it just depends on how well trained it is and the dataset.

But this is also entirely testable. I guarantee much like Go, if we set up a “human vs AI guess the blurry image” competition that AI will blow us out of the water. It’s simply a data * training issue, and humans don’t spend hours on end practicing enhancing images like they do playing Chess.

Again - it won’t be perfect, obviously. It will have false positives, of course.

Doesn’t mean it can’t be better than human.

Also GANs are pretty irrelevant, the model structure has nothing to do with the theory.

Re: Adobe Photoshop's 'super resolution' made my jaw hit the floor

#63

Post by perl4ever »

hojjat12000 wrote: post #47
nwienert wrote: post #37

Earlier quoted context omitted.

No there certainly is a chance for ML to improve here. Let’s take the classic example of enhancing a blurry photo to get a license plate. Humans may not be able to see much in the blur, but an AI trained on many different highly down-res’d images could at least give you plausible outcomes using far less data than a human brain would be able to say anything with confidence. You wouldn’t hold it up as the absolute trut…

Actually the opposite. These algorithms are more susceptible to noise, they may generate sharp perfect license plate numbers (that are totally fabricated and completely wrong) from a blurry image. But by no means should you even consider the results to have hints of truth. GAN produces totally different results if you slightly change the input. So, as others are also saying, these "enhances" are great for decoration…

>These algorithms are more susceptible to noise, they may generate sharp perfect license plate numbers (that are totally fabricated and completely wrong) from a blurry image.

This is not really an issue that is new or limited to things that are called AI.

https://www.theregister.com/2013/08/06/xerox_copier_flaw_mea...

Re: Adobe Photoshop's 'super resolution' made my jaw hit the floor

#65

Post by perl4ever »

intricatedetail wrote: post #56

I hate articles where author shows an option but won't actually tell where it is located in the application. I spent 10 minutes looking for it in latest PS and couldn't find it. Then I clicked at link to related article about "Enhance Details" and it seems like the option could be in Lightroom instead? I tried to use it myself because the illustrations in the article don't look to impressive, but authors enthusiasm g…

What I felt was missing was a "conventional" enlargement with the previous best algorithm side by side with the AI one.

Re: Adobe Photoshop's 'super resolution' made my jaw hit the floor

#66

Post by AmVess »

robk wrote: post #36

Topaz Gigapixel is quite good though despite the negative comments in the article. I'd rather give my money to Topaz for this one feature than keep paying Adobe subscription fees indefinitely

I've been using it for a year. Each version gets a little better than the last and it gets regular updates.

It also has the rather large benefit of not being tied to Creative Cloud, which is one of the worst bits of software ever made.

Re: Adobe Photoshop's 'super resolution' made my jaw hit the floor

#67

Post by roughly »

rozab wrote: post #61
roughly wrote: post #30

Earlier quoted context omitted.

I think this point is worth pushing on a bit harder, which is to say that the "additional details" in the picture are guesses by the software, not actual additional details. The data present in the picture is fixed, the software uses that data to build educated guesses on what was actually there. If the photo doesn't contain enough data to actually determine what a given piece of text in the image says, the software…

In some use cases, like OCR, the accuracy of these guesses can be established in a scientific way. And it tends to be very good.

I agree; I'd say two things in response, though:

1. However good the guess is, it's still just that: a guess. Taking the standard of "evidence in a murder case", the OCR can and probably should be used to point investigators in the right direction so they can go and collect more data, but it should not be considered sufficient as evidence itself.

2. OCR is a relatively constrained solution space - success in those conditions doesn't mean the same level of accuracy can or will be reached outside of that constrained space.

To be clear, though - I'm making a primarily epistemic argument, not one based on utility. There are a lot of areas for which these kind of machine guessing systems are of enormous utility, we just shouldn't confuse what they're doing with actual data collection.

Re: Adobe Photoshop's 'super resolution' made my jaw hit the floor

#68

Post by kqr »

roughly wrote: post #53
smnrchrds wrote: post #50

Earlier quoted context omitted.

I hope such photos are submitted as camera takes them. With our without this new feature, photoshopping a photo before presenting it to court must be illegal.

If you consider photos taken by cell phones, it's hard to really say what "as the camera takes them" means - a lot of ML-driven retouching happens "automagically" with most modern cell phones already and I'd expect more in the future.

It goes even further than that. Image sensors don't capture images. They record electricity that can be interpreted as an image.

This might seem like a quibble, but once you dive a little deeper into it, you realise that there's enormous latitude and subjectivity in the way you do that interpretation.

What's even crazier is that this didn't come with digital photography. Analogue film photography has the same problem. The silver on the film doesn't become an image until it's interpreted by someone in the darkroom.

There is no such thing as an objective photograph. It's always a subjective interpretation of an ambiguous record.

Re: Adobe Photoshop's 'super resolution' made my jaw hit the floor

#69

Post by 0-_-0 »

jl6 wrote: post #64

Is it just me who found the article immensely frustrating for lacking same-region-crop side by side comparisons?

Exactly, an article about superresolution doesn't atually show what superresolution is doing, despite the terribly clickbait-y headline.
Post reply on HN