Collision detection for physics / ray tracing for arbitrary meshes is slow, unless they are pre-processed as SDF or decomposed into convex parts. However, there was no suitable solution for animated meshes until now

https://www.youtube.com/watch?v=ihaBIAjh5_s [www.youtube.com]

We are developing a Houdini plugin for approximate decomposition of the animated mesh into non-rigid convex parts. Animations were pre-processed (trained) in 30s - 4min (it could be more for more detailed animations). The approximation error can be chosen afterwards interactively (0-2s). The method is robust to topologically incoherent meshes (degenerate triangles, open meshes, self-intersections, etc), which commonly happened in all these animations.
The model can be trained for one video (or a set of videos) and evaluated on another, if vertices correspond to each other (for example a rigged character for a game or a movie).

Evaluation runs in real-time. We originally developed it for our fluid solver ( https://www.youtube.com/watch?v=55rsJI11FOA [www.youtube.com] - a Houdini plugin under progress), but there are many applications, such as ray tracing. If you have any other application in mind, please let us know.

This is great I'd use it all the time for collisions, shadows & emitters.

Also… get Alembic & bgeo (+VDB) i/o into your fluid software, add accurate real-time cloth/viscera and you're set for life I reckon.