Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Neural Supersampling for Real-Time Rendering. Parent comment
The inputs are similar:
https://www.nvidia.com/content/dam/en-zz/Solutions/geforce/n...
In contrast to DLSS1, the output of the NN is not color values, but sampling locations and weights, to look up the color values from the previous low-resolution frames.
There are no comments on this comment yet.
The inputs are similar:
https://www.nvidia.com/content/dam/en-zz/Solutions/geforce/n...
In contrast to DLSS1, the output of the NN is not color values, but sampling locations and weights, to look up the color values from the previous low-resolution frames.