You are viewing the course site for a past offering of this course. The current offering may be found here.
Lecture 10: Ray Tracing Acceleration (46)
ZizhengTai

Can we use classification techniques to try to approach this? For example, we can try to find an SVM classifier that divide the objects as evenly as possible? We can assign each object a random class at the beginning, and iteratively try to give them a new class that minimizes the loss in some way...?

j316chuck

I think SVM or Unsupervised K means may work but it would probably be slower than the BVH split algorithm which runs on O(N)

You must be enrolled in the course to comment