Running the model on 2 RGBD images

[seann999]

I am trying to run this on 2 images taken from a RealSense.
Is there code or documentation I can look at to know how to input these into the model?

[seann999]

I was able to somewhat understand some of the data from reading the preprocessing scripts, but I do not understand how to obtain sample_pts in a real setting

It seems to be extracted from sim, which for simulated data is extracted from the physics engine. How do you obtain this in a real setting? Is it even required?

ACID/PlushSim/scripts/attic_scene.py

Lines 226 to 236 in c1ff2ad

	def get_scene_state_plush(self,raw=False,convert_to=None):
	sim,vis = self._get_plush_points()
	loc,rot,scale = self._get_plush_loc(),self._get_plush_rot(),self._get_plush_scale()
	if not raw:
	loc,rot,scale = tuple(loc),eval(str(rot)),tuple(scale)
	state = {'sim':sim, 'vis':vis,
	'loc':loc, 'rot':rot, 'scale':scale}
	if convert_to is not None:
	for k,v in state.items():
	state[k] = np.array(v, convert_to)
	return state