I hope some day this will generalize to video. I don't care about the exact shape of background trees in an action movie - with this approach, they could be compressed to just a few bytes, regardless of resolution.
PixelNN – Example-Based Image Synthesis
21–30 of 155 posts
Re: PixelNN – Example-Based Image Synthesis
#22Seems to have a thing for beards.
Re: PixelNN – Example-Based Image Synthesis
#23A pair of the inputs in the edge-to-edge faces are swapped. I have nagged an author.
Re: PixelNN – Example-Based Image Synthesis
#24Earlier quoted context omitted.
Approaches like these are hallucinating the high resolution images though--not something that we'd ever want being used for police work. That said, I wonder if it would perform better than eyewitness testimony...
You could e.g. ostensibly produce valid license plates, which could be further reduced by matching the car color and model, to produce a small set of calid records.
Such an algorithm would likely get the state wrong. This is error prone and fraught with real world difficulties that could get people shot.
Re: PixelNN – Example-Based Image Synthesis
#25I found the title somewhat misleading. I was expecting some clever application of the nearest-neighbor interpolation. But this seems to involve neural nets and appears far from "simple" to me (I'm not in the image processing field though).
Re: PixelNN – Example-Based Image Synthesis
#26I hope some day this will generalize to video. I don't care about the exact shape of background trees in an action movie - with this approach, they could be compressed to just a few bytes, regardless of resolution.
That's what video compression does now.
Re: PixelNN – Example-Based Image Synthesis
#27Earlier quoted context omitted.
No, but think of these blurred images as a "hash" - in an ideal situation, you only have one value that encodes to a certain hash value, right? So If you are given a hash X you technically can work out that it was derived from value Y - you're not getting back information that was lost - in a way it was merely encoded into the blurred image, and it should be possible to produce a real image which, when blurred, will…
> you only have one value that encodes to a certain hash value, right? Errr wrong. A perfect hash, yes. But they're never perfect. You have a collision domain and you hope that you don't have enough inputs to trigger a birthday paradox. Look at the pictures on the article. It's an outline of the shoe. That's your hash. ANY shoe with that general outline resolves to that same hash. If your input is objects found in th…
Fortunately there is a limit: the universe (in a practical sense). You cannot encode all states it has in a hash as it would require more states than you want to encode as you already mentioned (pigeon hole). But representing macroscopic data like text (or basically anything bigger than atomic scale) uniquely can be done with 128+ bits. Double that and you are likely safe for collisions, assuming the method you use is uniform and not biased to some input.
If you want ease collision examples you can take a look at people using CRC32 as hashes/digests. It is notoriously prone to collisions (since only 32 bits).
Re: PixelNN – Example-Based Image Synthesis
#28I used to roll my eyes at crime television shows, whenever they said "Enhance" for a low quality image. Now it seems the possibility of that becoming realistic are increasing with a steady clip, based on this paper and other enhancement techniques I've seen posted here.
Approaches like these are hallucinating the high resolution images though--not something that we'd ever want being used for police work. That said, I wonder if it would perform better than eyewitness testimony...
It would be useful to reduce the number of suspects... calculate possible combinations, match them against the mugshots database and investigate/interrogate those people. Or if you're the NSA/KGB, you can match against the social media pictures database, and then ask the social media company to tell you where these users were at the time of the crime (since the social media app on the phone track their users' location...)
Re: PixelNN – Example-Based Image Synthesis
#29I used to roll my eyes at crime television shows, whenever they said "Enhance" for a low quality image. Now it seems the possibility of that becoming realistic are increasing with a steady clip, based on this paper and other enhancement techniques I've seen posted here.
Except, and this is really the fundamental catch, it's not so much "enhance" as it is "project a believable substitute/interpretation". You fundamentally can't get back information that has been destroyed/or never captured in the first place. What you can do is fill in the gaps/information with plausible values. I don't know whether this sounds like I'm splitting hairs, but it's really important that the general publ…
What you can do though, in limited circumstances, is create a still picture with more detail from a lower quality video.
https://photo.stackexchange.com/questions/17098/csi-image-re...
Re: PixelNN – Example-Based Image Synthesis
#30So is there an analagous process that would apply to audio I wonder?
There kind of already is audio equivalent: MIDI. It supplies low resolution timing and pitch information and it's up to synthesizer to produce audio output matching those data.