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

TL;DR

TIPSy-GAN introduces a novel method for unsupervised 2D to 3D human pose estimation by training separate generators for different body parts, improving accuracy and stability over previous approaches.

Contribution

The paper proposes training spatially independent generators for different body parts and introduces new consistency constraints, enhancing unsupervised 3D pose estimation accuracy and training stability.

Findings

Decreases average error by 17% on Human3.6M dataset.

Outperforms other unsupervised methods in 3D pose estimation.

Shows improved stability with dual-generator adversarial training.

Abstract

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 a single spatially codependent structure; in fact, we posit 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 coordinates of all other keypoints. To investigate our hypothesis 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 self-consistency cycle is key to lowering the evaluation error and therefore introduce new consistency constraints during training. A TIPSy model is produced via knowledge distillation from these generators which can predict the 3D ordinates for the entire 2D pose with improved results. Furthermore, we address an unanswered question in prior work of how long to train in a truly unsupervised scenario. We show that for two independent generators training adversarially has improved stability than that of a solo generator which collapses. TIPSy decreases the average error by 17\% when compared to that of a baseline solo generator on the Human3.6M dataset. 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 datasets.