02/02/2021

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

Chenxin Xu, Siheng Chen, Maosen Li, Ya Zhang

Keywords:

Abstract Paper Similar Papers

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.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38947882
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 2:56 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 14:06 
 0
 0
 0
 0
 10:07 
 0
 0
 0
 0
 7:14 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:50 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 9:03 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 5:35 
 0
 0
 0
 0
 12:59 
 0
 0
 0
 0
 3:06 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 14:18 
 0
 0
 0
 0
 10:10 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 15:07 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 14:54 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 15:44 
 0
 0
 0
 0
 13:41 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 15:50 
 0
 0
 0
 0
 4:21 
 0
 0
 0
 0
 14:58 
 0
 0
 0
 0
 1:03 
 0
 0
 0
 0
 10:03 
 0
 0
 0
 0
 4:37 
 0
 0
 0
 0
 3:35 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 4:36 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 0:57 
 0
 0
 0
 0
 19:03 
 0
 0
 0
 0
 1:01