# Benchmarking 3D Human Pose Estimation Models under Occlusions

arXiv: https://arxiv.org/abs/2504.10350 · HTML: https://mlsanity.com/paper/2504.10350/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 64 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 30 of 31)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [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)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [Ordinal Depth Supervision for 3D Human Pose Estimation](https://mlsanity.com/paper/1805.04095/) (2018)
- [PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2303.17472/) (2023)
- [Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation](https://mlsanity.com/paper/2303.11579/) (2023)
- [P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.07628/) (2022)
- [Conditional Directed Graph Convolution for 3D Human Pose Estimation](https://mlsanity.com/paper/2107.07797/) (2021)
- [Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats](https://mlsanity.com/paper/2212.14474/) (2022)
- [DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model](https://mlsanity.com/paper/2212.02796/) (2022)
- [Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation](https://mlsanity.com/paper/2307.03833/) (2023)
- [How Robust is 3D Human Pose Estimation to Occlusion?](https://mlsanity.com/paper/1808.09316/) (2018)
- [FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models](https://mlsanity.com/paper/2405.05216/) (2024)
- [AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements](https://mlsanity.com/paper/2405.12070/) (2024)
- [Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration](https://mlsanity.com/paper/2304.04437/) (2023)
- [Markerless human pose estimation for biomedical applications: a survey](https://mlsanity.com/paper/2308.00519/) (2023)
- [Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes](https://mlsanity.com/paper/2308.00628/) (2023)
- [AnimePose: Multi-person 3D pose estimation and animation](https://mlsanity.com/paper/2002.02792/) (2020)
- [LInKs "Lifting Independent Keypoints" -- Partial Pose Lifting for Occlusion Handling with Improved Accuracy in 2D-3D Human Pose Estimation](https://mlsanity.com/paper/2309.07243/) (2023)
- [Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework](https://mlsanity.com/paper/2203.04113/) (2022)
- [Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion](https://mlsanity.com/paper/2410.04574/) (2024)

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

- [SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarking](https://mlsanity.com/paper/2602.20792/) (2026)
- [Evaluation of Pose Estimation Systems for Sign Language Translation](https://mlsanity.com/paper/2604.24609/) (2026)
- [Toward Reliable Infant Pose Estimation: A Training-Dynamics Approach to Noisy Annotation Detection](https://mlsanity.com/paper/2610.06423/) (2026)

## Abstract (arXiv)

Human Pose Estimation (HPE) involves detecting and localizing keypoints on the human body from visual data. In 3D HPE, occlusions, where parts of the body are not visible in the image, pose a significant challenge for accurate pose reconstruction. This paper presents a benchmark on the robustness of 3D HPE models under realistic occlusion conditions, involving combinations of occluded keypoints commonly observed in real-world scenarios. We evaluate nine state-of-the-art 2D-to-3D HPE models, spanning convolutional, transformer-based, graph-based, and diffusion-based architectures, using the BlendMimic3D dataset, a synthetic dataset with ground-truth 2D/3D annotations and occlusion labels. All models were originally trained on Human3.6M and tested here without retraining to assess their generalization. We introduce a protocol that simulates occlusion by adding noise into 2D keypoints based on real detector behavior, and conduct both global and per-joint sensitivity analyses. Our findings reveal that all models exhibit notable performance degradation under occlusion, with diffusion-based models underperforming despite their stochastic nature. Additionally, a per-joint occlusion analysis identifies consistent vulnerability in distal joints (e.g., wrists, feet) across models. Overall, this work highlights critical limitations of current 3D HPE models in handling occlusions, and provides insights for improving real-world robustness.