chenxuluo / epc Goto Github PK

Hello Chenxu Luo

Thank you very much for your interesting work. I have questions on the formulas in your paper. The rigid background Mb in equation 3 doesn't seem to be correct. The second term seems to be phi (ps | Ds) instead of (pt | Dt), because this mask says that the rigid background pixels should have the same back projection in the 3D space.

The Md seems also strange to me because the first back projection is in the coordinate system of the source frame, while the second back projection is in the coordinate system of the target frame. Are you sure you don't need to multiply a T?

Thank you very much in advance.

Best regards
Hai Li

Very interesting work. Eagerly waiting

Great work! Can you please let me know how to train or test the model?
Thanks