Question about pose preprocessing

Hi,

I have a question about retrieving the pose data.
As referenced below, after the pose is converted from quaternion to matrix, it follows by an inverse operation. Why is this inverse operation necessary?

DeepV2D/deepv2d/data_stream/nyuv2.py

Lines 112 to 113 in eb362f2

    
           pose_mat = pose_vec2mat(pose_vec) 
        
           poses.append(np.linalg.inv(pose_mat))

Thanks

The inverse operator converts poses from "world" coordinates to "camera" coordinates. This is necessary because we use camera coordinates for training.

	pose_mat = pose_vec2mat(pose_vec)
	poses.append(np.linalg.inv(pose_mat))