Neural Supersampling for Real-Time Rendering

Re:Neural Supersampling for Real-Time Rendering by Jasper_ on Saturday July 04, 2020 @10:31AM (#23732436)

It's basically just a good TAA and the tensor cores are basically used as a poor man's Lanczos. The tensor cores are used for obfuscation, and to make sure it doesn't run on AMD. Very little about DLSS 2.0 is "DL".

[ Parent | on HN ]

Re:Neural Supersampling for Real-Time Rendering by bcatanzaro on Saturday July 04, 2020 @04:37PM (#23734761)

This is inaccurate.

[ Parent | on HN ]

Re:Neural Supersampling for Real-Time Rendering by david-gpu on Saturday July 04, 2020 @05:15PM (#23734967)

Please be aware that the parent is Brian Catanzaro, VP of Applied Deep Learning Research at NVidia, who overviews the development of DLSS among many other things.

If he says that the GP is inaccurate, trust him.

Hi, Brian!

[ Parent | on HN ]