DeepVO-pytorch icon indicating copy to clipboard operation
DeepVO-pytorch copied to clipboard

code question

Open ujgygy656565 opened this issue 5 years ago • 3 comments

ang = eulerAnglesToRotationMatrix([0, answer[-1][0], 0]) location = ang.dot(predict_pose_seq[-1][3:]) predict_pose_seq[-1][3:] = location[:] last_pose = predict_pose_seq[-1]

I don't understand these steps.Can you explain these for me? I look forward to your reply. Thank you.

ujgygy656565 avatar Jul 11 '19 02:07 ujgygy656565

Hi, i have the same question as you. Have you solved this question?

SherlockGH avatar Aug 23 '19 13:08 SherlockGH

same question :(

mrgransky avatar Oct 21 '19 08:10 mrgransky

The first line gets the rotation matrix. The second line multiplies the rotation matrix by the predicted pose; so it comes in the right way according to the last pose and rotation. In the third and forth line it applies these changes so that we have the right pose in continuous of the poses till now.

mrdavoodi avatar May 15 '21 10:05 mrdavoodi