"Teaching Independent Parts Separately"(TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Human Pose Estimation

05/12/2022
by   Peter Hardy, et al.
0

We present TIPSy-GAN, a new approach to improve the accuracy and stability in unsupervised adversarial 2D to 3D human pose estimation. In our work we demonstrate that the human kinematic skeleton should not be assumed as one spatially codependent structure. In fact, we believe when a full 2D pose is provided during training, there is an inherent bias learned where the 3D coordinate of a keypoint is spatially codependent on the 2D locations of all other keypoints. To investigate our theory we follow previous adversarial approaches but train two generators on spatially independent parts of the kinematic skeleton, the torso and the legs. We find that improving the 2D reprojection self-consistency cycle is key to lowering the evaluation error and therefore introduce new consistency constraints during training. A TIPSy is produced model via knowledge distillation from these generators which can predict the 3D coordinates for the entire 2D pose with improved results. Furthermore, we address the question left unanswered in prior work detailing how long to train for a truly unsupervised scenario. We show that two independent generators training adversarially has improved stability than that of a solo generator which will collapse due to the adversarial network becoming unstable. TIPSy decreases the average error by 18 baseline solo generator. TIPSy improves upon other unsupervised approaches while also performing strongly against supervised and weakly-supervised approaches during evaluation on both the Human3.6M and MPI-INF-3DHP dataset.

READ FULL TEXT
research
09/01/2022

Optimising 2D Pose Representation: Improve Accuracy, Stability and Generalisability Within Unsupervised 2D-3D Human Pose Estimation

This paper addresses the problem of 2D pose representation during unsupe...
research
04/09/2019

Unsupervised 3D Pose Estimation with Geometric Self-Supervision

We present an unsupervised learning approach to recover 3D human pose fr...
research
09/13/2023

LInKs "Lifting Independent Keypoints" – Partial Pose Lifting for Occlusion Handling with Improved Accuracy in 2D-3D Human Pose Estimation

We present LInKs, a novel unsupervised learning method to recover 3D hum...
research
06/24/2020

Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation

Estimation of 3D human pose from monocular image has gained considerable...
research
08/22/2018

Can 3D Pose be Learned from 2D Projections Alone?

3D pose estimation from a single image is a challenging task in computer...
research
12/17/2020

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

We propose a novel method based on teacher-student learning framework fo...
research
05/13/2021

When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

Human pose estimation is a fundamental yet challenging task in computer ...

Please sign up or login with your details

Forgot password? Click here to reset