A Question Regarding the Transformation Matrix T in model.py

[wzx0826]

Thank you for your excellent work! I’ve been thoroughly impressed with the clarity and quality of the codebase, which has made it easy to follow and learn from.

I have a question about the transformation matrix logic in model.py (lines 203-209). I noticed that when frame_id = 0, T is set to the identity matrix, while for other frame_id values, it's set to cam_T_cam.

I'm curious about the design rationale behind this approach. Could you please help me understand what purpose this implementation serves?

Thanks in advance for your time and insights!