# 3D Human Pose Estimation with Relational Networks

arXiv: https://arxiv.org/abs/1805.08961 · HTML: https://mlsanity.com/paper/1805.08961/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2018.

## Built on by (most cited first, 10 of 10)

- [Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation](https://mlsanity.com/paper/2108.07181/) (2021)
- [Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices](https://mlsanity.com/paper/2201.12382/) (2022)
- [A Review of Emerging Research Directions in Abstract Visual Reasoning](https://mlsanity.com/paper/2202.10284/) (2022)
- [MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning](https://mlsanity.com/paper/2404.13591/) (2024)
- [Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation](https://mlsanity.com/paper/2107.13994/) (2021)
- [Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework](https://mlsanity.com/paper/2203.04113/) (2022)
- [Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation](https://mlsanity.com/paper/2304.12069/) (2023)
- ["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)
- [Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives](https://mlsanity.com/paper/2307.13541/) (2023)

## Abstract (arXiv)

In this paper, we propose a novel 3D human pose estimation algorithm from a single image based on neural networks. We adopted the structure of the relational networks in order to capture the relations among different body parts. In our method, each pair of different body parts generates features, and the average of the features from all the pairs are used for 3D pose estimation. In addition, we propose a dropout method that can be used in relational modules, which inherently imposes robustness to the occlusions. The proposed network achieves state-of-the-art performance for 3D pose estimation in Human 3.6M dataset, and it effectively produces plausible results even in the existence of missing joints.