[falcor84]

It's really cool, but I can't shake off an "uncanny valley" feeling, with all of the small quirks in the geometry. What I think I'd be interested in is a post-processing step where this splat is automatically converted to a 3d model that approximates each component, only falling back to the point cloud if there's no simple shape that fits the observation at a particular location.

[c-fe]

This is close to the idea of convex splatting (recent paper) in which convex shapes are used to approximate these real 3d objects as they are better suited than gaussians

[lbeckman314]

https://convexsplatting.github.io/

TIL — very cool work!