High-res image reconstruction, latent diffusion models from human brain activity

Re:High-res image reconstruction, latent diffusion models fr... by armchairhacker on Friday April 28, 2023 @07:36PM (#35748496)

fMRI is extremely coarse-grained, it also only measures blood flow. There's no way you can reconstruct what a person is thinking from just that, except at a really basic level.

If we want better brain-to-machine interfaces we'll need to work on better non-invasive (or at least invasive but low-risk) brain imaging

[ Parent | on HN ]

Re:High-res image reconstruction, latent diffusion models fr... by macawfish on Friday April 28, 2023 @08:43PM (#35748868)

I have a feeling this is going to involve NIR-II with fluorescent particles. To be clear, I'm not advocating for this, the thought of it freaks me out. Just because something isn't physically invasive, doesn't mean it isn't invasive in other ways!

[ Parent | on HN ]

Re:High-res image reconstruction, latent diffusion models fr... by flangola7 on Friday April 28, 2023 @08:59PM (#35748947)

It freaks you out? Isn't NIR dye pretty safe to use?

[ Parent | on HN ]

Re:High-res image reconstruction, latent diffusion models fr... by morkalork on Friday April 28, 2023 @09:08PM (#35749003)

Me thinks it's the thought that it could work that is freaky, not the mechanism itself. If you think governments demanding backdoors to encryption is bad now, what if that tech worked? All it would take is a kidnapping case like in "The Cell" for things to get very uncomfortable.

[ Parent | on HN ]

Re:High-res image reconstruction, latent diffusion models fr... by mrbungie on Friday April 28, 2023 @10:14PM (#35749396)

Reading thoughts is the ultimate invasion of privacy. Nothing weird about that freaking people out.

[ Parent | on HN ]

Re:High-res image reconstruction, latent diffusion models fr... by magicalhippo on Friday April 28, 2023 @09:06PM (#35748986)

There's magnetoencephalography[1][2] which from what I could see offers a more direct route to measure brain activity.

[1]: https://en.wikipedia.org/wiki/Magnetoencephalography

[2]: https://hebergement.universite-paris-saclay.fr/supraconducti...

[ Parent | on HN ]

Re:High-res image reconstruction, latent diffusion models fr... by lostlogin on Saturday April 29, 2023 @07:56AM (#35752097)

MEG has much better temporal resolution than MR, but it’s spatial resolution is only marginally better (according to the below source, figure 6). However it doesn’t help that MR has a vast array of acquisition methods and techniques.

The below link is also interesting for its discussion of fMRI.

https://www.nature.com/scitable/blog/brain-metrics/what_does...

[ Parent | on HN ]