# Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2012.09398 · HTML: https://mlsanity.com/paper/2012.09398/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2020.

## Built on by (most cited first, 10 of 10)

- [EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning](https://mlsanity.com/paper/2303.10876/) (2023)
- [Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction](https://mlsanity.com/paper/2208.00368/) (2022)
- [Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction](https://mlsanity.com/paper/2308.08942/) (2023)
- [Deep Non-rigid Structure-from-Motion: A Sequence-to-Sequence Translation Perspective](https://mlsanity.com/paper/2204.04730/) (2022)
- [MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views](https://mlsanity.com/paper/2207.09086/) (2022)
- [Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling](https://mlsanity.com/paper/2308.10705/) (2023)
- [PoseGU: 3D Human Pose Estimation with Novel Human Pose Generator and Unbiased Learning](https://mlsanity.com/paper/2207.03618/) (2022)
- [Multi-person 3D pose estimation from unlabelled data](https://mlsanity.com/paper/2212.08731/) (2022)
- ["Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation](https://mlsanity.com/paper/2205.05980/) (2022)
- [Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle](https://mlsanity.com/paper/2309.06313/) (2023)

## Abstract (arXiv)

We propose a novel method based on teacher-student learning framework for 3D human pose estimation without any 3D annotation or side information. To solve this unsupervised-learning problem, the teacher network adopts pose-dictionary-based modeling for regularization to estimate a physically plausible 3D pose. To handle the decomposition ambiguity in the teacher network, we propose a cycle-consistent architecture promoting a 3D rotation-invariant property to train the teacher network. To further improve the estimation accuracy, the student network adopts a novel graph convolution network for flexibility to directly estimate the 3D coordinates. Another cycle-consistent architecture promoting 3D rotation-equivariant property is adopted to exploit geometry consistency, together with knowledge distillation from the teacher network to improve the pose estimation performance. We conduct extensive experiments on Human3.6M and MPI-INF-3DHP. Our method reduces the 3D joint prediction error by 11.4% compared to state-of-the-art unsupervised methods and also outperforms many weakly-supervised methods that use side information on Human3.6M. Code will be available at https://github.com/sjtuxcx/ITES.