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

12/17/2020
by   Chenxin Xu, et al.
0

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 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.

READ FULL TEXT

page 7

page 9

research
01/15/2020

Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning

We present MoVNect, a lightweight deep neural network to capture 3D huma...
research
07/16/2020

Self-supervision on Unlabelled OR Data for Multi-person 2D/3D Human Pose Estimation

2D/3D human pose estimation is needed to develop novel intelligent tools...
research
03/07/2020

PoseNet3D: Unsupervised 3D Human Shape and Pose Estimation

Recovering 3D human pose from 2D joints is a highly unconstrained proble...
research
04/21/2021

Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation

Although deep convolution neural networks (DCNN) have achieved excellent...
research
03/15/2022

Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation

A well-designed strong-weak augmentation strategy and the stable teacher...
research
08/18/2019

Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning

We propose to learn a 3D pose estimator by distilling knowledge from Non...

Please sign up or login with your details

Forgot password? Click here to reset