Open jonilaserson opened 1 year ago
I think this is related to this issue: https://github.com/facebookresearch/pytorch3d/issues/1436 from a few months ago. Didn't get a response there yet either.
Yes, I transform_points_screen
is known to behave differently for different camera types, and I don't think it's going to be fixed because fixing it could be quite disruptive.
The cameras doc says that:
in_ndc=False
), thentransform_points
projects the world to screen space.transform_points_screen
should also project the world to screen space.Hence, the world point [-1, 0, 1] is to the right of point [0, 0, 1] in world coordinates, and should have a higher x value in screen space.
However in the output of the code below, the opposite is true, which is not the expected behavior.
Output:
On the other hand, using
cam.transform_points_screen(points)
in the last line returns the expected output:However, it's
transform_points
with its unexpected behavior that is used in all the main project and unproject methods. Is there a good reason whytransform_points
on screen cameras doesn't behave like the defaulttransform_points_screen
and according to the docs?