# Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation

arXiv: https://arxiv.org/abs/2304.12069 · HTML: https://mlsanity.com/paper/2304.12069/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 24 Apr 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [Graph Stacked Hourglass Networks for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.16385/) (2021)
- [Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.14304/) (2021)
- [P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.07628/) (2022)
- [3D Human Pose Estimation from a Single Image via Distance Matrix Regression](https://mlsanity.com/paper/1611.09010/) (2016)
- [3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training](https://mlsanity.com/paper/2004.11822/) (2020)
- [CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.13387/) (2022)
- [3D Human Pose Estimation with Relational Networks](https://mlsanity.com/paper/1805.08961/) (2018)
- [Exploring Severe Occlusion: Multi-Person 3D Pose Estimation with Gated Convolution](https://mlsanity.com/paper/2011.00184/) (2020)
- [3D Human Pose Regression using Graph Convolutional Network](https://mlsanity.com/paper/2105.10379/) (2021)
- [Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework](https://mlsanity.com/paper/2203.04113/) (2022)

## Built on by (most cited first, 3 of 3)

- [Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning](https://mlsanity.com/paper/2404.05218/) (2024)
- [Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images](https://mlsanity.com/paper/2407.09694/) (2024)
- [Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach](https://mlsanity.com/paper/2607.00716/) (2026)

## Abstract (arXiv)

Occlusion is an omnipresent challenge in 3D human pose estimation (HPE). In spite of the large amount of research dedicated to 3D HPE, only a limited number of studies address the problem of occlusion explicitly. To fill this gap, we propose to combine exploitation of spatio-temporal features with synthetic occlusion augmentation during training to deal with occlusion. To this end, we build a spatio-temporal 3D HPE model, StridedPoseGraphFormer based on graph convolution and transformers, and train it using occlusion augmentation. Unlike the existing occlusion-aware methods, that are only tested for limited occlusion, we extensively evaluate our method for varying degrees of occlusion. We show that our proposed method compares favorably with the state-of-the-art (SoA). Our experimental results also reveal that in the absence of any occlusion handling mechanism, the performance of SoA 3D HPE methods degrades significantly when they encounter occlusion.