Greg Miller

And just like Death Stranding 2 animator Mike York suggested, it seems the algorithm is just taking frames from the game along with motion vector data and drawing a new image that's pasted on top.

When Owen asked whether or not the model is just taking a rendered frame as input, Freeman responded, quote, yes, DLSS 5 takes a 2D frame plus motion vectors as input, end quote.

Then he clarified, quote, DLSS 5 is trained end-to-end to understand complex scene schematics such as characters, hair, fabric, and translucent skin, along with environmental lighting conditions like front lit, back lit, or overcast, lit, not lit.

all by analyzing a single frame, end quote.

NVIDIA has made the claim about quote-unquote complex scene schematics before, but because the model is only taking the rendered frame and motion data as input, it has no way to know definitively the values given to various in-game objects by developers.

Owen was told the same thing I've been told by NVIDIA too, that developers will have, quote, detailed controls, such as intensity and color grading.

Artists can use these controls to adjust global contrast, saturation, and gamma, and determine where and how enhancements are applied to maintain a game's unique aesthetic, end quote.

But given what NVIDIA has shared about how the model works, these controls seem limited to the kind of sliders you'd find in Adobe Lightroom.

We've talked it today.

There's a lot of shows last week about how a lot of show.

Yikesy, yikesy, yikesy.

And here we are again.

Yikesy.

Mike, you got anything new to say under the sun about this?

Other than you hope people just don't use it.

Yeah.

Well, I don't love that.

That's where, you know, Jensen would pop up and say you're completely wrong.

Exactly.

We will continue to watch this nightmare unfold and see if anyone actually tries it.