# It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data

arXiv: https://arxiv.org/abs/1805.06880 · HTML: https://mlsanity.com/paper/1805.06880/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2018.

## Built on by (most cited first, 5 of 5)

- [KAMA: 3D Keypoint Aware Body Mesh Articulation](https://mlsanity.com/paper/2104.13502/) (2021)
- [Deep Monocular 3D Human Pose Estimation via Cascaded Dimension-Lifting](https://mlsanity.com/paper/2104.03520/) (2021)
- [Human Modelling and Pose Estimation Overview](https://mlsanity.com/paper/2406.19290/) (2024)
- ["Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation](https://mlsanity.com/paper/2205.05980/) (2022)
- [Optimising 2D Pose Representation: Improve Accuracy, Stability and Generalisability Within Unsupervised 2D-3D Human Pose Estimation](https://mlsanity.com/paper/2209.00618/) (2022)

## Abstract (arXiv)

We address the problem of 3D human pose estimation from 2D input images using only weakly supervised training data. Despite showing considerable success for 2D pose estimation, the application of supervised machine learning to 3D pose estimation in real world images is currently hampered by the lack of varied training images with corresponding 3D poses. Most existing 3D pose estimation algorithms train on data that has either been collected in carefully controlled studio settings or has been generated synthetically. Instead, we take a different approach, and propose a 3D human pose estimation algorithm that only requires relative estimates of depth at training time. Such training signal, although noisy, can be easily collected from crowd annotators, and is of sufficient quality for enabling successful training and evaluation of 3D pose algorithms. Our results are competitive with fully supervised regression based approaches on the Human3.6M dataset, despite using significantly weaker training data. Our proposed algorithm opens the door to using existing widespread 2D datasets for 3D pose estimation by allowing fine-tuning with noisy relative constraints, resulting in more accurate 3D poses.