Method MAE(R) R2 (R) MAE(t) R2 (t) Random sampling 1.689 0.927 0.011 0.997 Closeness to other points 2.109 0.861 0.013 0.995 L

We thank reviewers for taking the time to consider our NeurIPS submission. Table 2 shows PRNet consistently outperforms PointNetLK in all settings. PRNet is on a par with PointNetLK while being slower than DCP . We will add "Deep Part Induction from Articulated Object Pairs" to related works and discuss We believe these comments will help to make the work stronger.