Project website: https://sites.google.com/view/useek. The paper is available at https://arxiv.org/abs/2209.13864.

• 1_train_merger.py trains the teacher network, following the procedure in Skeleton Merger with minor adaptations.
• 2_prepare_segment.py prepares the segmentation pseudo labels for the student network.
• 3_train_useek.py trains the student network, which is adapted from the segmentation network of SPRIN.
• 4_predictor_keypointnet.py and 5_eval_keypointnet.py test the student network on the KeypointNet dataset with SE(3) transformations.

The ShapeNetCore.v2 dataset used for training is available from the Point Cloud Datasets repository.

The pre-trained models for both the teacher and student networks are available at Google Drive.