I've seen quite a few NeRF demos so far, but it appears that all of them are not much more than slightly distorting and remixing the input images. Also in these examples, the water looks like plastic and the NeRF clearly cannot reproduce the colorful grass but instead turns it into one large smooth surface.
But without transparency effects, all of this can be rendered fast and efficiently using geometric textures - i.e. what the Unreal Engine 5 uses. Here's how "traditional" real-time rendering looks like:
https://www.youtube.com/watch?v=PBktSo0bXas
Compared to that, I find "AI rendering" which is blurry and much slower (15fps @ 800px) somewhat underwhelming.
In case anyone here is working on AI rendering, I'd suggest that you focus on transparent glass. That's where all game engines slow down 2x to 4x because of the need to render things in multiple passes. So if you can make fake glass look nice, that's when AI rendering becomes a useful improvement over the state of the art.
As for the scenes in this demo, I'm pretty sure that structure from motion + mesh reduction + normal mapping can reconstruct the original images almost pixel-perfect, and at 200+ fps on modern GPUs. So there's simply not much benefit to having a neural raymarcher over a highly optimized raycaster.
But without transparency effects, all of this can be rendered fast and efficiently using geometric textures - i.e. what the Unreal Engine 5 uses. Here's how "traditional" real-time rendering looks like:
https://www.youtube.com/watch?v=PBktSo0bXas
Compared to that, I find "AI rendering" which is blurry and much slower (15fps @ 800px) somewhat underwhelming.
In case anyone here is working on AI rendering, I'd suggest that you focus on transparent glass. That's where all game engines slow down 2x to 4x because of the need to render things in multiple passes. So if you can make fake glass look nice, that's when AI rendering becomes a useful improvement over the state of the art.
As for the scenes in this demo, I'm pretty sure that structure from motion + mesh reduction + normal mapping can reconstruct the original images almost pixel-perfect, and at 200+ fps on modern GPUs. So there's simply not much benefit to having a neural raymarcher over a highly optimized raycaster.