Re:RenderFormer: Neural Rendering of Triangle Meshes with Gl...
by jsheard on Sunday June 01, 2025 @03:36AM
(#44149258)
Yeah, and the big caveat with this approach is that the runtime complexity is quadratic with scene complexity, as opposed to the usual methods which are logarithmic. It's a cool potential direction for further research, but there's a way to go before it can wrangle real production scenes.
[ Parent
| on HN ]
Re:RenderFormer: Neural Rendering of Triangle Meshes with Gl...
by monster_truck on Sunday June 01, 2025 @04:47AM
(#44149517)
I'd sooner expect them to use this to 'feed' a larger neural path tracing engine where you can get away with 1 sample every x frames. Those already do a pretty great job of generating great looking images from what seems like noise.
I don't think this conventional similarity matrix in the paper is all that important to them