Early Access: Inside DLSS 4 & Nvidia Machine Learning: The Bryan Catanzaro Interview (Patreon)

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. Want some DF-branded tee-shirts, mugs, hoodies and various items based on DF catchphrases? Check out our store: https://store.digitalfoundry.net Join the DF Supporter Program for pristine video downloads, behind the scenes content, early access to DF Retro, early access to DF Direct Weekly and much, much more: https://bit.ly/3jEGjvx Subscribe for more Digital Foundry: http://bit.ly/DFSubscribe 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?