Closed cww97 closed 3 years ago
Sorry for the delay, we are both very busy these days. You don't need to use align_mat. camera_pose[n] record the transformation matrix from the first camera pose to the n^th camera pose. camera_pose[i] and camera_pose[j] will be enough.
I see version 1.2.6 supports
transform
for grasps, f312d7e2a73ca97f9e791cf3f1ab3aeacebac3e9I have another idea: I found that the grasps are all in camera coordinate, I am in
ann_id == i
but I wanna to use grasp inann_id == j
, seems I need thisI guess I can get some idea from here
but my mind is still all a mess about how could I construct this matrix T