# Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/1809.04987 · HTML: https://mlsanity.com/paper/1809.04987/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2018.

## Built on by (most cited first, 8 of 8)

- [Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking](https://mlsanity.com/paper/2101.08466/) (2021)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement](https://mlsanity.com/paper/2210.13529/) (2022)
- [The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimation](https://mlsanity.com/paper/2205.00508/) (2022)
- [Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input](https://mlsanity.com/paper/2312.06797/) (2023)
- [Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometries](https://mlsanity.com/paper/2405.11677/) (2024)
- [Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGB](https://mlsanity.com/paper/2409.11104/) (2024)
- [Object Detection During Newborn Resuscitation Activities](https://mlsanity.com/paper/2303.07790/) (2023)

## Abstract (arXiv)

In this paper we present our winning entry at the 2018 ECCV PoseTrack Challenge on 3D human pose estimation. Using a fully-convolutional backbone architecture, we obtain volumetric heatmaps per body joint, which we convert to coordinates using soft-argmax. Absolute person center depth is estimated by a 1D heatmap prediction head. The coordinates are back-projected to 3D camera space, where we minimize the L1 loss. Key to our good results is the training data augmentation with randomly placed occluders from the Pascal VOC dataset. In addition to reaching first place in the Challenge, our method also surpasses the state-of-the-art on the full Human3.6M benchmark among methods that use no additional pose datasets in training. Code for applying synthetic occlusions is availabe at https://github.com/isarandi/synthetic-occlusion.