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

What an unprocessed photo looks like

maurycyz.com

Post reply on HN
Print view View original

371–380 of 418 posts

Re: What an unprocessed photo looks like

#371

Post by lifeisstillgood »

bborud wrote: post #308
lifeisstillgood wrote: post #279

Ok I just never imagined that photons hitting camera lenses would not produce a “raw” image that made sense to my eyes - I am stunned and this is a fantastic addition to the canon of things one should know about the modern world. (I also just realised that the world become more complex than I could understand when some guy mixed two ochres together and finger painted a Woolly Mammoth.)

Your brain does a far more impressive job of fooling you into believing that the image you see of your surroundings in your brain is actually what your sensory apparatus is seeing. It very much isn’t. Just the mechanism to cope with your eye movement without making you woozy is, by itself, a marvel. Our brains are far more impressive than what amounts to fairly trivial signal processing done on digital images.

That reminds me of the explanation of why sometimes you look at the second hand of a clock and it seems like it takes longer than a second to tick- because your brain is actually (IIRR) delaying and extending the time it sends the image (I think)

Re: What an unprocessed photo looks like

#372

Post by jiggawatts »

trashb wrote: post #295
jiggawatts wrote: post #256

Earlier quoted context omitted.

Sure, and my camera can do bird eye detection and whatnot too, but that's a very lightweight model running in-body. Probably just a fine-tuned variant of something like YOLO. I've seen only a couple of papers from Google talking about stacking multiple frames from a DSLR, but that was only research for improving mobile phone cameras. Ironically, some mobile phones now have more megapixels than my flagship full-frame…

A DSLR and mobile phone camera optimize for different things and can't really be compared. Mobile phone camera's are severely handicapped by the optics & sensor size. Therefore to create a acceptable picture (to share on social media) they need to do a lot of processing. DSLR and professional camera's feature much greater hardware. Here the optics and sensor size/type are important it optimize the actual light being…

> A DSLR and mobile phone camera optimize for different things and can't really be compared.

You sound exactly like the sales guy trying to explain why that Indigo workstation is “different” even though it was performing the exact same vector and matrix algebra as my gaming GPU. The. Exact. Same. Thing.

Everything else you’ve said is irrelevant to computational photography. If anything, it helps matters because there’s better raw data to work with.

The real reason is that one group had to solve these problems, the other could keep making excuses for why it was “impossible” while the problem clearly wasn’t.

And anyway, what I’m after isn’t even in-body processing! I’m happy to take the RAW images and grind them through an AI that barely fits into a 5090 and warms my room appreciably for each photo processed.

Re: What an unprocessed photo looks like

#373

Post by liampulles »

kuschku wrote: post #298
liampulles wrote: post #216

Earlier quoted context omitted.

The bit about the green over-representation in camera color filters is partially correct. Human color sensitivity varies a lot from individual to individual (and not just amongst individuals with color blindness), but general statistics indicate we are most sensitive to red light. The main reason is that green does indeed overwhelmingly contribute to perceptual luminance (over 70% in sRGB once gamma corrected: https:…

> Small neural networks I believe are the current state of the art (e.g. train to reverse a 16x16 color filter pattern for the given camera). What is currently in use by modern digital cameras is all trade secret stuff. Considering you usually shoot RAW, and debayer and process in post, the camera hasn't done any of that. It's only smartphones that might be doing internal AI Debayering, but they're already hallucinat…

Sure - if you don't want to do demosaicing on the camera, that's fine. It doesn't mean there is not an algorithm there as an option.

If you care about trying to get an image that is as accurate as possible to the scene, then it is well within your interest to use a Convolutional Neural Network based algorithm, since these are amongst the highest performing in terms of measured PSNR (which is what nearly all demosaicing algorithms in academia are measured on). You are maybe thinking of generative AI?

Re: What an unprocessed photo looks like

#374

Post by cge »

brookst wrote: post #96
barishnamazov wrote: post #7

I love posts that peel back the abstraction layer of "images." It really highlights that modern photography is just signal processing with better marketing. A fun tangent on the "green cast" mentioned in the post: the reason the Bayer pattern is RGGB (50% green) isn't just about color balance, but spatial resolution. The human eye is most sensitive to green light, so that channel effectively carries the majority of t…

Even old school chemical films were the same thing, just different domain. There is no such thing as “unprocessed” data, at least that we can perceive.

Yes. Writing a post like this, but for film, would be illustrative of that similarity, but significantly more challenging to represent, especially for color film. I actually don't know the whole process in enough detail to write one, and the visualizations would be difficult, but the processing is there.

You have layers of substrate with silver halides, made sensitive to different frequency ranges with sensitizing dyes, crystallized into silver halide crystals, rather than a regular grid of pixels; you take a photo that is not an image, but a collection of specks of metallic silver. Through a series of chemical reactions, you develop those specks. Differences in chemistry, in temperatures, in agitation, in the film, all affect what for digital images is described as processing. Then in printing, you have a similar process all over again.

If anything, one might argue that the digital process allows a more consistent and quantitative understanding of the actual processing being done. Analog film seems like it involves less processing only because, for most people, the processing was always a black box of sending off the film for development and printing.

Re: What an unprocessed photo looks like

#375

Post by cge »

acomjean wrote: post #175
kdazzle wrote: post #163

Earlier quoted context omitted.

Exactly - film photographers heavily process(ed) their images from the film processing through to the print. Ansel Adams wrote a few books on the topic and they’re great reads. And different films and photo papers can have totally different looks, defined by the chemistry of the manufacturer and however _they_ want things to look.

Excepting slide photos. No real adjustment once taken (a more difficult medium than negative film which you can adjust a little when printing) You’re right about Ansel Adams. He “dodged and burned” extensively (lightened and darkened areas when printing.) Photoshop kept the dodge and burn names on some tools for a while. https://m.youtube.com/watch?v=IoCtni-WWVs When we printed for our college paper we had a dial tha…

>Excepting slide photos. No real adjustment once taken (a more difficult medium than negative film which you can adjust a little when printing)

One might argue that there, many of the processing choices are being made by the film manufacturer, in the sensitizing dyes being used, etc.

Re: What an unprocessed photo looks like

#376

Post by emodendroket »

Dylan16807 wrote: post #222
emodendroket wrote: post #9

This is actually really useful. A lot of people demand an "unprocessed" photo but don't understand what they're actually asking for.

They probably do know what they're asking for, they're just using an ambiguous word.

I don't really think so! I think they imagine that if there were no processing applied to the image it would look pretty much like what they see IRL but that's not true.

Re: What an unprocessed photo looks like

#377

Post by phendrenad2 »

jibal wrote: post #346
lnenad wrote: post #343

Earlier quoted context omitted.

Saying you're being too pedantic is an insult? Wasn't intended to be.

Random ad hominem criticisms from strangers are insulting. Stick to substance and stop insulting people and then pretending you didn't. Over and out.

At some point after ever conversation terminates in you getting a "random ad hominem" you have to re-evaluate the thought process that led you to that point.

Re: What an unprocessed photo looks like

#378

Post by yencabulator »

skrebbel wrote: post #251
shagie wrote: post #101

Earlier quoted context omitted.

> A fun tangent on the "green cast" mentioned in the post: the reason the Bayer pattern is RGGB (50% green) isn't just about color balance, but spatial resolution. The human eye is most sensitive to green light, so that channel effectively carries the majority of the luminance (brightness/detail) data. From the classic file format "ppm" (portable pixel map) the ppm to pgm (portable grayscale map) man page: https://li…

> The quantization formula ppmtopgm uses is g = .299 r + .587 g + .114 b. Seriously. We can trust linux man pages to use the same 1-letter variable name for 2 different things in a tiny formula, can't we?

Yes, let's blame the documentation for a program from 1989 on a kernel from 1991.

Re: What an unprocessed photo looks like

#379

Post by fsckboy »

barishnamazov wrote: post #7

I love posts that peel back the abstraction layer of "images." It really highlights that modern photography is just signal processing with better marketing. A fun tangent on the "green cast" mentioned in the post: the reason the Bayer pattern is RGGB (50% green) isn't just about color balance, but spatial resolution. The human eye is most sensitive to green light, so that channel effectively carries the majority of t…

>It really highlights that modern photography is just signal processing with better marketing

your perception of the world is just signal processing that's susceptible to marketing

Re: What an unprocessed photo looks like

#380

Post by fragmede »

yencabulator wrote: post #378
skrebbel wrote: post #251

Earlier quoted context omitted.

> The quantization formula ppmtopgm uses is g = .299 r + .587 g + .114 b. Seriously. We can trust linux man pages to use the same 1-letter variable name for 2 different things in a tiny formula, can't we?

Yes, let's blame the documentation for a program from 1989 on a kernel from 1991.

Well, we can't blame that on an LLM in any case
Post reply on HN