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

Edge detection doesn’t explain line drawing

aaronhertzmann.com

Post reply on HN
Print view View original

151–160 of 174 posts

Re: Edge detection doesn’t explain line drawing

#151

Post by OJFord »

willis936 wrote: post #147
olaulaja wrote: post #75

Earlier quoted context omitted.

Sounds like using the wrong metric, the upscaled image should be compared against the original full resolution one, not the downscaled one. Obviously you can't know what the full resolution one looks like when actually upscaling (vs testing), but you can make an educated guess.

You can remove the guesswork. You can start with a high resolution (or even raster export of a vector image for an extreme example), downsample it (various methods and downsampling factors for completeness), then attempt to upscale it.

That's exactly what GP is talking about, the 'guesswork' comes in when you upscale as a function of only the downsampled version.

Re: Edge detection doesn’t explain line drawing

#152

Post by detourdog »

milesvp wrote: post #144
detourdog wrote: post #134

Earlier quoted context omitted.

What I wonder about from your explanation is how does a simulation know where the noise is coming from. I feeling is that inside the simulation one is unable to differentiate the source of the noise.

You're not wrong. But I suspect you'd find inconsistencies if you looked hard enough. Situations where 2 things don't interact in some obvious expected way. And that's just the simple case. If you've played enough video games, you'd know that devs can easily create scenarios where there is no way to get the correct behavior between 2 objects without doing some pretty drastic changes to their game engine. (I play a lo…

For the record I'm in the reflection of reality camp. I think the simulation camp is silly.

Re: Edge detection doesn’t explain line drawing

#153

Post by brap »

This was a very interesting read.

From childhood we instinctively draw lines, but I never questioned how we produce them from real objects, and why they work so well at representing real objects. It’s one of those things we just take for granted.

Re: Edge detection doesn’t explain line drawing

#154

Post by OJFord »

pbhjpbhj wrote: post #115
Kinrany wrote: post #37

Earlier quoted context omitted.

The upscaled image stores more information than the original image, so it must be possible to keep all the information while still doing edge enhancement!

Stores more data, but the same information, and if there is any interpolation then some of the data is modified, meaning that you lose a little data. In fact even without interpolation I think you change the data. If you imagine a hard edge that aligns with a pixel [ ] boundary then you imagine upscaling in various ways, I think it's QED. You change data about the sharpness of the edge. [ ] I use an Android phone, wi…

Surely anything other than duplicating each pixel x times both horizontally and vertically (so 1 turns into 4, or 9, or 16, ...) adds information?

(This submission is going to have me reaching for my old textbooks.. about time really!)

Re: Edge detection doesn’t explain line drawing

#155

Post by geon »

OJFord wrote: post #154
pbhjpbhj wrote: post #115

Earlier quoted context omitted.

Stores more data, but the same information, and if there is any interpolation then some of the data is modified, meaning that you lose a little data. In fact even without interpolation I think you change the data. If you imagine a hard edge that aligns with a pixel [ ] boundary then you imagine upscaling in various ways, I think it's QED. You change data about the sharpness of the edge. [ ] I use an Android phone, wi…

Surely anything other than duplicating each pixel x times both horizontally and vertically (so 1 turns into 4, or 9, or 16, ...) adds information? (This submission is going to have me reaching for my old textbooks.. about time really!)

No. Nearest neighbor, bilinear bicubic etc. is just encoding the same information in different ways.

You could add noise, or generate new details with an ai upscaler. That would create new information.

Re: Edge detection doesn’t explain line drawing

#156

Post by thehappypm »

aftbit wrote: post #57
cvoss wrote: post #45

The brain's ability to do "shadow removal" is really impressive. You can see it happening in the final example depicted in the article. I think this ability is what was used to explain "the dress". It also comes up in a classic optical illusion [0] where a checkerboard of light and dark gray squares has an object sitting on it and casting a shadow. The shadowed light gray squares are exactly the same shade as the uns…

Hey thanks, this one is new to me. 100% it is impossible to convince myself that those two squares are the same color. I have a camera looking over my driveway with motion detection that triggers all the time because of the shadow of a tree waving in the wind. My current weekend project is to use FastSAM to detect cars / animals / people in the driveway instead of just looking at a threshold of changed pixels. 1: htt…

It's because the squares are not the same color.

The alternating squares are different colors... in absence of a shadow.

Your brain is correctly adjusting for the shadow to correctly identify the "true" color.

Re: Edge detection doesn’t explain line drawing

#157

Post by OJFord »

geon wrote: post #155
OJFord wrote: post #154

Earlier quoted context omitted.

Surely anything other than duplicating each pixel x times both horizontally and vertically (so 1 turns into 4, or 9, or 16, ...) adds information? (This submission is going to have me reaching for my old textbooks.. about time really!)

No. Nearest neighbor, bilinear bicubic etc. is just encoding the same information in different ways. You could add noise, or generate new details with an ai upscaler. That would create new information.

Ah, right, anything that's a function purely of what's in the image - no randomness, no external context/'knowledge' to interpret it semantically, is as you say 'encoding the same information in different ways'?

If it can be computed (deterministically) from the image alone, then it was already there.

Re: Edge detection doesn’t explain line drawing

#158

Post by dredmorbius »

detourdog wrote: post #60
CuriouslyC wrote: post #20

Earlier quoted context omitted.

The difference is turtles all the way down was literal, but heavenly clockwork and computer program perspectives are clear metaphors.

I first heard Turtles all the way down in spoken story by Kurt Vonnegut. Does anyone else have a source of the story or is that the source?

Quote Investigator traces variants back as far as 1626, though it evolves over time. A "rocks all the way down" variant dates to 1838, "tortoises all the way down" to 1854:

https://quoteinvestigator.com/2021/08/22/turtles-down/>

The version I'd first heard attributed the story to a lecture by Bertrand Russell and an audience Q&A, though it seems clear that that couldn't have been the first instance.

Re: Edge detection doesn’t explain line drawing

#159

Post by detourdog »

dredmorbius wrote: post #158
detourdog wrote: post #60

Earlier quoted context omitted.

I first heard Turtles all the way down in spoken story by Kurt Vonnegut. Does anyone else have a source of the story or is that the source?

Quote Investigator traces variants back as far as 1626, though it evolves over time. A "rocks all the way down" variant dates to 1838, "tortoises all the way down" to 1854: https://quoteinvestigator.com/2021/08/22/turtles-down/ > The version I'd first heard attributed the story to a lecture by Bertrand Russell and an audience Q&A, though it seems clear that that couldn't have been the first instance.

Your source story sounds like the story I heard/read Kurt Vonnegut tell,

Re: Edge detection doesn’t explain line drawing

#160

Post by dredmorbius »

dylan604 wrote: post #55
hprotagonist wrote: post #8

Earlier quoted context omitted.

ah, someone who paid attention in lecture! (incidentally; there’s a fairly deep literature of historians of science that have carefully documented that we describe ourselves as analogous to the most sophisticated technology of the day: see “to lose one’s temper”, “to blow a gasket”, “i got my wires crossed”, “sorry, cache miss”, … as metaphors and idioms of mental state through the centuries that reflect the cool tec…

>as metaphors and idioms of mental state through the centuries after listing a bunch of things from the previous century that barely stretches a bit further back. i would have been impressed if you had come up with a phrase from medieval tech, or roman/greek/egyptian. hell, i'd settle for pioneer days tech to allow for "centuries". otherwise, it just feels like modern day analogies.

Prior to the scientific age, most theory of mind was religious and/or philosophical, and models typically ran to mind/body duality (Descartes), ideals and essences (Plato & Aristotle, generally), or "spirit" which had numerous associations, many of them textual, which was itself the great technology of the Axial Age in which that concept emerged.

Otherwise, in the scientific and technical era, you have the brain as computer, as AI, as homonculus (which really doesn't explain much), as mechanism or clockwork, as a composed of parts (much as a factory or assembly-line, I suppose), and the like.

Post reply on HN