News for hackers. Stuff that matters.

A comment on The Limits of Computational Photography. Parent comment

Re:The Limits of Computational Photography by wombat_trouble on Tuesday January 31, 2023 @12:49AM (#34591689)
"Real" cameras do a lot of postprocessing too, but it's generally oriented at producing faithful results. They might remove unambiguous and correctable issues such as vignetting or lens distortion, but they don't cross the line of inventing new details to make the photo look good.

Computational photography techniques on smartphones, on the other hand, were always designed around squishy "user perception" goals to make photos look impressive, details be damned.

[ Parent | on HN ]
Re:The Limits of Computational Photography by jlarocco on Tuesday January 31, 2023 @01:04AM (#34591787)
I didn't see any invented "new details" in the article's iPhone photos. Phones have small sensors and crap lenses, so they ramp up noise reduction and sharpness to make up for it. Turn up the ISO and max out the NR on the Fujifilm and the results would be nearly as bad.
[ Parent | on HN ]
Re:The Limits of Computational Photography by wombat_trouble on Tuesday January 31, 2023 @01:48AM (#34592055)
I see invented texture and layering here: https://yager.io/comp/mi.jpeg
[ Parent | on HN ]
Re:The Limits of Computational Photography by kaba0 on Tuesday January 31, 2023 @03:25AM (#34592693)
That seems just like edge sharpening.
[ Parent | on HN ]
Re:The Limits of Computational Photography by jefftk on Tuesday January 31, 2023 @08:44AM (#34594904)
It's pretty hard to tell without knowing what sort of image was input to the computational photography process
[ Parent | on HN ]
Re:The Limits of Computational Photography by MichaelZuo on Tuesday January 31, 2023 @10:26AM (#34596253)
The actual image is right below it in the post.
[ Parent | on HN ]
Re:The Limits of Computational Photography by jefftk on Tuesday January 31, 2023 @10:45AM (#34596559)
That's the image captured by a different camera (it's labeled "Fujifilm X-T5" and is from a different angle). The input I'm interested here is what the phone camera's sensor received prior to processing.
[ Parent | on HN ]
Re:The Limits of Computational Photography by MichaelZuo on Tuesday January 31, 2023 @11:24AM (#34597211)
He mentions that the phone did display something close to that for a brief moment.
[ Parent | on HN ]
Re:The Limits of Computational Photography by wyager on Tuesday January 31, 2023 @08:46AM (#34594924)
The text looks qualitatively very little like the true text. Almost all details of the text (including shape of strokes!) are hallucinated by the iPhone.

I could import the X-T5 photo into lightroom or whatever and crank NR all the way up, and I don't think it would look anything like the iPhone image. Also, the less-processed image on the iPhone (which you see for a split second) looked fine, so there wasn't enough noise to justify this level of "correction".

My guess is the iPhone got confused by the texture of the anodized aluminum.

[ Parent | on HN ]
Re:The Limits of Computational Photography by wonnage on Tuesday January 31, 2023 @04:00AM (#34592907)
At the end of the day you're always "inventing new details" to turn sensor data into an image. Most algorithms involve edge detection and predicting color correlations, and you'll also run into cases where false details are added and reality is changed to fit the priors.

One can find pathological cases for traditional cameras too - moire is a common problem, Fuji X-Trans sensors historically had a watercolor/worms effect particularly in greenery, etc.

[ Parent | on HN ]