Shir Gur
Shir Gur
In my case, there's no need for it to be differentiable, only for visualization (with and without the mesh) I find it very easy to use PyTorch3D for training AND...
Hi! Any chance you spare us the features-extraction for the test-set and simply share it? Thank you!
This is only because we want to be consistent with "grid_sample" and "renderer" axis directions
Documents/examples about setting entity physcial properties(for domain randomization in RL training)
> > Thanks for bringing this up. Theoretically, we should be able to set most of the properties, but we need to write an interface to extract those tensor via...