I'm trying to reproduce the result on your paper with 3DMatch dataset, however, I only could find the code for pre-training each module (e.g. "Ref", "Desc", "KeyPt", and "Inlier").
Could you tell me how to train all four modules simultaneously as the final step?
I'm trying to reproduce the result on your paper with 3DMatch dataset, however, I only could find the code for pre-training each module (e.g. "Ref", "Desc", "KeyPt", and "Inlier"). Could you tell me how to train all four modules simultaneously as the final step?