Inside DLSS 4 & Nvidia Machine Learning: The Bryan Catanzaro Interview

The RTX 50-series cards are coming and at the forefront of Nvidia innovation is a full revamp of DLSS, with revised transformer model Super Resolution and Ray Reconstruction, along with up to 4x multi frame generation. At CES 2025, Alex had the opportunity to sit down and talk about the new technologies with Nvidia's Bryan Catanzaro, VP of Applied Deep Learning Research.

00:00 Introduction
00:48 Why switch from CNNs to transformers?
02:08 What are some image characteristics that are improved with DLSS 4 Super Resolution?
03:17 Is there headroom to continue to improve on Super Resolution?
04:12 How much more expensive is DLSS 4 Super Resolution to run?
05:25 How does the transformer model improve Ray Reconstruction?
09:43 Why is frame gen no longer using hardware optical flow?
13:06 Could the new Frame Generation run on RTX 3000?
13:44 What has changed for frame pacing with DLSS 4 Frame Generation?
15:37 Will Frame Generation ever support standard v-sync?
17:18 Could you explain how Reflex 2 works?
21:11 What is the lowest acceptable input frame-rate for DLSS 4 Frame Generation?
22:13 What does the future of real-time graphics look like?

[GeneralKenobi]

As a bald af 29 yo guy I feel personally attacked by this video

[TalonsTech]

Left = hair reconstruction ON
Right = hair reconstruction OFF

[StoneyWoney]

I like this new Nvidia Hairworks version

[Die-Coughman]

Say what you want about the people that market and price nvidia's cards but I am so thankful for the engineers in Nvidia's R&D

[AJsWorld]

Comments be like:
DLSS/AI ❌
Dude’s hair ✅

[fruitcake]

Bryan's hair is the ground truth for all the innovative hair techniques

[amnforge]

Bryan's hair is DLSS version 9999; Fantastic hair.

[Benefits]

To all the hardworking engineers in the tech field out there - Thank you for what you do.

[sapphyrus]

I love how Bryan reveals to us that we have been practically faking 3D graphics for 50 years and proposes that AI generation can help with that faking being more accurate.

[zedsdeadbaby]

I really like his frank explanation for why they decided to drop the optical flow sensor for mfg. It took them years to get it right, and they dropped it after one gen in favor of a new tensor-heavy approach. Technology is a function of the time it was in, and sometimes you just have to move on if you want results. No wonder nvidia is on the top of their game

[missfortune]

Bryan Catanzaro, Mark Cerny... all these industry legends watch DF and love it, that's awesome to see!

[eggcitedbro]

10:11 “Technology is always a function of the time in which it’s built” is a great quote from this - great engineering perspective to implement solutions with new technology based on what’s currently available.

This goes double here since they’re literally the one who are paving things to work this time around by putting out tensor core consumer GPUs out there over the past few years.

[joross]

Not many groups who could put on an interview like this. Kudos to Alex and Digital Foundry! Great interview.

[zachb]

You definitely need to test the performance hit of DLSS 4 on 4000 vs 5000 at the same base resolution.

[Wobbotherd]

Catanzaro is brilliant. From CUDNN to this. What a time to be alive!

[tomd.]

Digital Foundry is my favorite channel... always something new and relevant every time

[what-divb]

thank you to whoever setup this interview, and thanks to alex for having an amazing set of questions! this is a fantastic video.

[johnc]

DLSS quality mode already looked really good. Excited for this new model.

[jayblaze]

Did he imply multi frame gen could come to older GPUs?

[Battler]

that was a non-answer on the 3000 series question.

I love the surprise.