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
Yes, you can!
First, you'd better retrain the model on your dataset, for different datasets have different data distributions and shape scales.
Second, after retraining, we offer two kinds of methods to cut the shape as half or octant. To be specific, we unset the SDF of cut part of the shape. Please refer to generate_from_partial_input in evaluation_scripts/eval_shape_comp.py for more details.
Thanks for your works! Can we use our own data to do point completion? How to do it?
The text was updated successfully, but these errors were encountered: