Pr-VIPE: View-Invariant Probabilistic Embedding for Human Pose

We propose an approach for learning a compact view-invariant probabilistic embedding space for 3D human poses from their 2D projections. Please refer to our ECCV'20 paper, IJCV'21 paper, and website for more details.

Contact

• Ting Liu
• Jennifer J. Sun
• Liangzhe Yuan

Updates

• 12/03/2021: Added Temporal Pr-VIPE training support. Please refer to our IJCV'21 paper for details.
• 11/23/2021: Added individual random keypoint dropout support. Please refer to our IJCV'21 paper for details.
• 03/25/2021: Moved the Pr-VIPE project code into the pr_vipe folder.
• 03/17/2021: Fixed an issue in camera augmentation.
• 03/04/2021: Added a program for running model inference.
• 10/21/2020: Added cross-view pose retrieval evaluation frame keys.
• 10/15/2020: Added training TFRecords generation program.
• 07/02/2020: First release. Included core TensorFlow code for model training.