Ask HN: Is Gaussian Splattering useful for analyzing Pretti's death?
4 comments
I agree with you this would be valuable, mostly for persuading the general public.
The skepticism you're getting amounts to "biased people/government won't care no matter what" and "fancy tech makes the evidence look more doctored, not less." They're not wrong but there are some disputes this could settle. Some people have argued that the moment where an ICE agent appears to withdraw Pretti's gun might just be him retrieving his own fumbled gun. Maybe a synthesized view could clear that up.
Personally, I think it will come down to the moment where one goon said "He's got a gun" and another one took that as license to shoot him three times. The other 6 or so gunshots were a kneejerk pile-on to that cowardly act.
So much for the 2nd Amendment, right?
No, it isn't.
1. The videos we have make it very obvious that he was murdered without any justification.
2. People who claim that he wasn't don't care about evidence. Even more, they're inclined towards conspiracies and a complex tool that edits video will only add more supicion, more things to quibble about. It wouldn't clarify anything, it would just muddy the waters more.
Who do you think you're going to convince and of what? I don't get how you can look at what happened and think "do you know what we need? - an obscure peace of complex video editing technology, that will sort this out".
1. The videos we have make it very obvious that he was murdered without any justification.
2. People who claim that he wasn't don't care about evidence. Even more, they're inclined towards conspiracies and a complex tool that edits video will only add more supicion, more things to quibble about. It wouldn't clarify anything, it would just muddy the waters more.
Who do you think you're going to convince and of what? I don't get how you can look at what happened and think "do you know what we need? - an obscure peace of complex video editing technology, that will sort this out".
Why would we want to do this when we can just watch each video in a sequence and pull out relevant clips or frames?
There's no issue with the angle. All angles tell the same story with varying levels of detail: he was trying to protect a woman, he was beaten, he was pepper sprayed, his gun was taken from his belt, and then he was murdered.
There is no alternative narrative supported by the videos.
There's no issue with the angle. All angles tell the same story with varying levels of detail: he was trying to protect a woman, he was beaten, he was pepper sprayed, his gun was taken from his belt, and then he was murdered.
There is no alternative narrative supported by the videos.
I believe your speculation that this would be useful is incorrect for two reasons.
1. The administration and it's sycophants do not accept evident reality. 2. The administration is destroying/tampering evidence and outright refusing to investigate.
While I respect the thought put in, we're a long way from this.
Perhaps in a more just world, phones would be equipped with a camera mode for recording facts. This removes any filtering or modification, tags with location and available data, and then uploads to a national archive for use in investigations.
1. The administration and it's sycophants do not accept evident reality. 2. The administration is destroying/tampering evidence and outright refusing to investigate.
While I respect the thought put in, we're a long way from this.
Perhaps in a more just world, phones would be equipped with a camera mode for recording facts. This removes any filtering or modification, tags with location and available data, and then uploads to a national archive for use in investigations.
My speculation is that it would be useful to: (1) synchronize video, (2) get more detail than a single camera can get, (3) track objects (like Pretti's gun) that are seen by multiple cameras, and (4) identify AI generated video.
The last is most important to me. There is a danger of AI generated or modified video of an event. It seems possible to me that Gaussian Splattering from N videos will be able to detect if the N+1 video is consistent or inconsistent with the scene.
Is this possible?