With BVH, the partitioning is fundamentally over lists of objects rather than space; if you split by space, you can/will have objects on both sides of the splitting plane, leading to duplicate references.
Doing it by lists means there are no duplicate references, however the combined bounding volumes can overlap, which is to be minimised, subject to the Surface Area Heuristic cost. It winds up being something like a quicksort, although for the highest quality acceleration structures you also want to do spatial clipping... this is an extremely deep field, and several people have spent considerable part of their professional career to it, for example the amazing Intel Embree guys :)
It also happens to work out best for GPU traversal algorithms, which was investigated by software simulation quite a few years ago by the now-legendary Finnish Nvidia team, and together with improvements on parallel BVH building methods and further refinements is basically what today's RTX technology is. (As far as I'm reading from the literature over the years.)
Here's a fundamental paper to get started: https://research.nvidia.com/publication/understanding-effici... (Note that these are the same Finnish geniuses behind so many things... Umbra PVS, modern alias-free GAN methods, stochastic sampling techniques, ...)
With BVH, the partitioning is fundamentally over lists of objects rather than space; if you split by space, you can/will have objects on both sides of the splitting plane, leading to duplicate references.
Doing it by lists means there are no duplicate references, however the combined bounding volumes can overlap, which is to be minimised, subject to the Surface Area Heuristic cost. It winds up being something like a quicksort, although for the highest quality acceleration structures you also want to do spatial clipping... this is an extremely deep field, and several people have spent considerable part of their professional career to it, for example the amazing Intel Embree guys :)
It also happens to work out best for GPU traversal algorithms, which was investigated by software simulation quite a few years ago by the now-legendary Finnish Nvidia team, and together with improvements on parallel BVH building methods and further refinements is basically what today's RTX technology is. (As far as I'm reading from the literature over the years.)
Here's a fundamental paper to get started: https://research.nvidia.com/publication/understanding-effici... (Note that these are the same Finnish geniuses behind so many things... Umbra PVS, modern alias-free GAN methods, stochastic sampling techniques, ...)