# Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network

arXiv: https://arxiv.org/abs/1711.10872 · HTML: https://mlsanity.com/paper/1711.10872/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2017.

## Built on by (most cited first, 11 of 11)

- [Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera](https://mlsanity.com/paper/2106.08059/) (2021)
- [NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representations](https://mlsanity.com/paper/2207.10985/) (2022)
- [Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution](https://mlsanity.com/paper/2204.13062/) (2022)
- [Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks](https://mlsanity.com/paper/2103.06982/) (2021)
- [Multi-View Video-Based 3D Hand Pose Estimation](https://mlsanity.com/paper/2109.11747/) (2021)
- [HandFlow: Quantifying View-Dependent 3D Ambiguity in Two-Hand Reconstruction with Normalizing Flow](https://mlsanity.com/paper/2210.01692/) (2022)
- [Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks](https://mlsanity.com/paper/2109.05776/) (2021)
- [Hand Visibility Detector: Per-Keypoint Visibility Estimation for Hands](https://mlsanity.com/paper/2608.11574/) (2026)
- [MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model](https://mlsanity.com/paper/2302.08751/) (2023)
- [Mesh Represented Recycle Learning for 3D Hand Pose and Mesh Estimation](https://mlsanity.com/paper/2310.12189/) (2023)
- [UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation](https://mlsanity.com/paper/2605.17742/) (2026)

## Abstract (arXiv)

Learning and predicting the pose parameters of a 3D hand model given an image, such as locations of hand joints, is challenging due to large viewpoint changes and articulations, and severe self-occlusions exhibited particularly in egocentric views. Both feature learning and prediction modeling have been investigated to tackle the problem. Though effective, most existing discriminative methods yield a single deterministic estimation of target poses. Due to their single-value mapping intrinsic, they fail to adequately handle self-occlusion problems, where occluded joints present multiple modes. In this paper, we tackle the self-occlusion issue and provide a complete description of observed poses given an input depth image by a novel method called hierarchical mixture density networks (HMDN). The proposed method leverages the state-of-the-art hand pose estimators based on Convolutional Neural Networks to facilitate feature learning, while it models the multiple modes in a two-level hierarchy to reconcile single-valued and multi-valued mapping in its output. The whole framework with a mixture of two differentiable density functions is naturally end-to-end trainable. In the experiments, HMDN produces interpretable and diverse candidate samples, and significantly outperforms the state-of-the-art methods on two benchmarks with occlusions, and performs comparably on another benchmark free of occlusions.