Radiant Foam: Real-Time Differentiable Ray Tracing

Re:Radiant Foam: Real-Time Differentiable Ray Tracing by momojo on Tuesday February 04, 2025 @07:48PM (#42941771)

> This algorithm is much more efficient than typical ray tracing acceleration methods that rely on hierarchical acceleration structures with logarithmic query complexity.

This is a wild claim to just slip in. Can anyone expand?

[ Parent | on HN ]

Re:Radiant Foam: Real-Time Differentiable Ray Tracing by TinkersW on Tuesday February 04, 2025 @10:49PM (#42943494)

Em? Seems reasonable, ray tracing a BVH is inherently slow AF because it diverges like mad(SIMD no like).

[ Parent | on HN ]

Re:Radiant Foam: Real-Time Differentiable Ray Tracing by niederman on Wednesday February 05, 2025 @01:19PM (#42952827)

It's faster because there are only a constant number of other faces in a given cell to check to find where the ray exits. Then you can just traverse from cell to cell in this way, without using hierarchical bounding box checks like you normally would.

[ Parent | on HN ]

Re:Radiant Foam: Real-Time Differentiable Ray Tracing by momojo on Wednesday February 05, 2025 @05:37PM (#42956347)

So its not tree based? Is it a graph traversal of sorts?

[ Parent | on HN ]