code issue in EPro-PnP-6DoF

[XiaoHaoPan]

I would like to know where is the code to get the rotation pose after getting the cc_maps in the CDPN.py, after going through the Epro_PnP forword, thanks!

cc_maps = self.rot_head_net(features) # joints.shape [bs, 1152, 64, 64]

[Lakonik]

hi! you may be looking for this

EPro-PnP/EPro-PnP-6DoF/lib/test.py

Lines 227 to 229 in 5ee1525

	T_vectors, R_quats = pose_opt.split([3, 4], dim=-1) # (n, [3, 4])
	R_matrix = R.from_quat(R_quats[:, [1, 2, 3, 0]].cpu().numpy()).as_matrix() # (n, 3, 3)
	pose_est = np.concatenate([R_matrix, T_vectors.reshape(bs, 3, 1).cpu().numpy()], axis=-1)

[XiaoHaoPan]

This seems to be different from the way you get posture during training. Why?
_, _, pose_opt_plus, _, pose_sample_logweights, cost_tgt = epropnp.monte_carlo_forward( x3d, x2d, w2d, camera, cost_fun, pose_init=pose_gt, force_init_solve=True, with_pose_opt_plus=True)
The pose_gt here seems to come from pose.txt in the dataset.

[Lakonik]

In training we run EPro-PnP in the monte carlo probabilistic mode, which allows the gradients to back-propagate through the probability density. At test time, probabilistic inference is not necessary, so we simply solve the conventional PnP problem using non-linear least square.