You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I want to train MeshRCNN on a custom dataset.
When creating a dataset, if I know the focal length and sensor size of the actual camera, can I calculate "rot_mat" and "trans_mat" using those values? (Are "rot_mat", "trans_mat" only used to convert 3D model to 2D in MeshRCNN?)
Or should I assume sensor width=32mm and calculate "focal_length", "rot_mat", "trans_mat" like Pix3D dataset?
(Are "rot_mat" and "trans_mat" used in MeshRCNN besides converting 3D model to 2d?)
I would be very appreciate if you have time to reply.
The text was updated successfully, but these errors were encountered:
Hi. Thank you for the great work!
I want to train MeshRCNN on a custom dataset.
When creating a dataset, if I know the focal length and sensor size of the actual camera, can I calculate "rot_mat" and "trans_mat" using those values? (Are "rot_mat", "trans_mat" only used to convert 3D model to 2D in MeshRCNN?)
Or should I assume sensor width=32mm and calculate "focal_length", "rot_mat", "trans_mat" like Pix3D dataset?
(Are "rot_mat" and "trans_mat" used in MeshRCNN besides converting 3D model to 2d?)
I would be very appreciate if you have time to reply.
The text was updated successfully, but these errors were encountered: