Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation release_vxyf6bjsards5c45mj74tumc3i

by Chenxin Xu, Siheng Chen, Maosen Li, Ya Zhang

Released as a article .

2020  

Abstract

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.
In text/plain format

Archived Files and Locations

application/pdf  8.1 MB
file_k5germfatbh2posapwwbq744m4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-12-17
Version   v1
Language   en ?
arXiv  2012.09398v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 329e2f0c-09c8-443e-ae8c-9957e84a6161
API URL: JSON