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

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

17 Dec 2020arXiv:2012.09398archive 2025-07-28

Chenxin Xu, Siheng Chen, Maosen Li, Ya zhang

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sjtuxcx/ITES officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Human Pose EstimationKnowledge DistillationPose EstimationUnsupervised 3D Human Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised 3D Human Pose Estimation Human3.6M ITES-TS MPJPE 85.3 #4 of 12 Archive leaderboard report
Unsupervised 3D Human Pose Estimation Human3.6M ITES-TS P-MPJPE 59.8 #4 of 12 Archive leaderboard report
Unsupervised 3D Human Pose Estimation MPI-INF-3DHP ITES-TS AUC 35.2 #3 of 4 Archive leaderboard report
Unsupervised 3D Human Pose Estimation MPI-INF-3DHP ITES-TS PCK 68.2 #3 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionKnowledge Distillation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections