Decanus to Legatus: Synthetic training for 2D-3D human pose lifting

10/05/2022
by   Yue Zhu, et al.
4

3D human pose estimation is a challenging task because of the difficulty to acquire ground-truth data outside of controlled environments. A number of further issues have been hindering progress in building a universal and robust model for this task, including domain gaps between different datasets, unseen actions between train and test datasets, various hardware settings and high cost of annotation, etc. In this paper, we propose an algorithm to generate infinite 3D synthetic human poses (Legatus) from a 3D pose distribution based on 10 initial handcrafted 3D poses (Decanus) during the training of a 2D to 3D human pose lifter neural network. Our results show that we can achieve 3D pose estimation performance comparable to methods using real data from specialized datasets but in a zero-shot setup, showing the generalization potential of our framework.

READ FULL TEXT

page 13

page 19

page 20

research
04/21/2020

Towards Generalization of 3D Human Pose Estimation In The Wild

In this paper, we propose 3DBodyTex.Pose, a dataset that addresses the t...
research
07/24/2018

Learning Human Poses from Actions

We consider the task of learning to estimate human pose in still images....
research
10/01/2021

Stochastic Modeling for Learnable Human Pose Triangulation

We propose a stochastic modeling framework for 3D human pose triangulati...
research
03/14/2022

Panoptic animal pose estimators are zero-shot performers

Animal pose estimation is critical in applications ranging from life sci...
research
04/27/2018

A generalizable approach for multi-view 3D human pose regression

Despite the significant improvement in the performance of monocular pose...
research
07/23/2015

Human Pose Estimation with Iterative Error Feedback

Hierarchical feature extractors such as Convolutional Networks (ConvNets...
research
04/19/2021

EGL++: Extending Expected Gradient Length to Active Learning for Human Pose Estimation

State of the art human pose estimation models continue to rely on large ...

Please sign up or login with your details

Forgot password? Click here to reset