I have got the coordinates of the model in the pixel plane. How can I use pytorch3d for raster rendering without setting the camera?

[Luh1124]

❓ Questions on how to use PyTorch3D

NOTE: Please look at the existing list of Issues tagged with the label 'question](https://github.com/facebookresearch/pytorch3d/issues?q=label%3Aquestion) or ['how-to. Only open a new issue if you cannot find an answer there.

[bottler]

A camera needs to be specified for any of PyTorch3D renderers. If screen space is the same as world space then it may be that the relevant camera is an orthogonal camera which does nothing.

When you say "faster rendering", do you mean faster because the camera transformation can be omitted? A very small proportion of the time spent in rendering is the camera transformation, so you shouldn't expect much of a speedup from omitting that step.

If you mean faster for some other reason, then we need more information.