Export per-frame 3DGS: only export the canonical opacity

[ChenYutongTHU]

Dear authors,

Great thanks for releasing this nice project!

I have an issue regarding the export of per-frame 3DGS.
When saving the per-frame 3DGS, the code uses the canonical opacity before the deformation.

4DGaussians/utils/render_utils.py

Lines 3 to 18 in 843d5ac

	def get_state_at_time(pc,viewpoint_camera):
	means3D = pc.get_xyz
	time = torch.tensor(viewpoint_camera.time).to(means3D.device).repeat(means3D.shape[0],1)
	opacity = pc._opacity
	shs = pc.get_features
	# If precomputed 3d covariance is provided, use it. If not, then it will be computed from
	# scaling / rotation by the rasterizer.
	scales = pc._scaling
	rotations = pc._rotation
	cov3D_precomp = None
	means3D_final, scales_final, rotations_final, opacity_final, shs_final = pc._deformation(means3D, scales,
	rotations, opacity, shs,
	time)
	return means3D_final, scales_final, rotations_final, opacity, shs_final

However, in my dataset, only using the deformed opacity can provide correct rendering results. I wonder if this was designed on purpose.

Great thanks!