45 points summarity 5 hours ago 10 comments

amelius 3 hours ago | parent

Neat! And the video was pretty interesting!

Wait ... patent pending? Research done with public money? Yuck! Downvoted immediately.

summarity 18 minutes ago | parent

This isn’t my work - just sharing the approach. I agree this should have been an open and reproducible publication. It won’t be long for this to become a normal feature in neural rendering engines though, there’s (IMO) no breakthrough novel idea in this pipeline.

echelon 2 hours ago | parent

> patent pending

Ugh, more reason to want AI to automate research. No more patents.

This is going to be used to shake down teams that had no idea these folks happened to do this off in their own corner of the world.

mikeaskew4 2 hours ago | parent

Could you expand on that?

echelon 1 hour ago | parent

I would like to implement this feature in software.

Now I cannot legally do so. Not even in free software.

We have to wait 20 years for this shit to expire. And by that point half of the people here will be retired and technology will have moved on, but this one important technique and feature will still be locked away.

See also: gif, mp3, h.264/5, seam carving, the ribbon, etc.

nomel 32 minutes ago | parent

Isn't the alternative that everything stays secret/proprietary, forever?

ragebol 1 minute ago | parent

Or outside imagery: 3D printing, only took off after the patents expired. Which is now a huge industry. What could have been would that patent or with it expiring earlier?

Tepix 2 hours ago | parent

That's pretty close to magick. Kudos!

vonneumannstan 1 hour ago | parent

Am I mistaken in thinking this was already doable with diffusion models?

summarity 20 minutes ago | parent

Not with any amount of temporal cohesion. This is using neural rendering that can stay consistent across arbitrary lights and their movement. But the authors chose to go proprietary, hopefully we’ll get some open alternatives in the near future.