# HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty

arXiv: https://arxiv.org/abs/2111.01440 · HTML: https://mlsanity.com/paper/2111.01440/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 47 references that are in the map.
- First posted on arXiv 2 Nov 2021.

## Builds on (most cited first, 22 of 22)

- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [Fine-Grained Head Pose Estimation Without Keypoints](https://mlsanity.com/paper/1710.00925/) (2017)
- [Face Alignment in Full Pose Range: A 3D Total Solution](https://mlsanity.com/paper/1804.01005/) (2018)
- [PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model](https://mlsanity.com/paper/1803.08225/) (2018)
- [HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition](https://mlsanity.com/paper/1603.01249/) (2016)
- [Towards Large-Pose Face Frontalization in the Wild](https://mlsanity.com/paper/1704.06244/) (2017)
- [WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose](https://mlsanity.com/paper/2005.10353/) (2020)
- [Deep Directional Statistics: Pose Estimation with Uncertainty Quantification](https://mlsanity.com/paper/1805.03430/) (2018)
- [Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition](https://mlsanity.com/paper/1912.08077/) (2019)
- [A Vector-based Representation to Enhance Head Pose Estimation](https://mlsanity.com/paper/2010.07184/) (2020)
- [LAEO-Net: revisiting people Looking At Each Other in videos](https://mlsanity.com/paper/1906.05261/) (2019)
- [Single-Network Whole-Body Pose Estimation](https://mlsanity.com/paper/1909.13423/) (2019)
- [Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection](https://mlsanity.com/paper/1809.05590/) (2018)
- [Gaze Estimation for Assisted Living Environments](https://mlsanity.com/paper/1909.09225/) (2019)
- [KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressors](https://mlsanity.com/paper/1702.05085/) (2017)
- [Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment](https://mlsanity.com/paper/1905.08609/) (2019)
- [Attention-Oriented Action Recognition for Real-Time Human-Robot Interaction](https://mlsanity.com/paper/2007.01065/) (2020)

## Built on by (most cited first, 9 of 9)

- [DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles](https://mlsanity.com/paper/2302.01110/) (2023)
- [A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction](https://mlsanity.com/paper/2403.10511/) (2024)
- [Semi-Supervised Unconstrained Head Pose Estimation in the Wild](https://mlsanity.com/paper/2404.02544/) (2024)
- [Latent Embedding Clustering for Occlusion Robust Head Pose Estimation](https://mlsanity.com/paper/2403.20251/) (2024)
- [Anticipation through Head Pose Estimation: a preliminary study](https://mlsanity.com/paper/2408.05516/) (2024)
- [IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1](https://mlsanity.com/paper/2603.19625/) (2026)
- [Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models](https://mlsanity.com/paper/2605.19859/) (2026)
- [Coordinate Singularities Break Conformal Coverage for Gaze and Head Pose](https://mlsanity.com/paper/2607.02565/) (2026)
- [Human-Inspired Social Engagement Analysis via Interpretable Mutual Visual Attention](https://mlsanity.com/paper/2608.24580/) (2026)

## Abstract (arXiv)

In this paper we introduce a novel method to estimate the head pose of people in single images starting from a small set of head keypoints. To this purpose, we propose a regression model that exploits keypoints computed automatically by 2D pose estimation algorithms and outputs the head pose represented by yaw, pitch, and roll. Our model is simple to implement and more efficient with respect to the state of the art -- faster in inference and smaller in terms of memory occupancy -- with comparable accuracy. Our method also provides a measure of the heteroscedastic uncertainties associated with the three angles, through an appropriately designed loss function; we show there is a correlation between error and uncertainty values, thus this extra source of information may be used in subsequent computational steps. As an example application, we address social interaction analysis in images: we propose an algorithm for a quantitative estimation of the level of interaction between people, starting from their head poses and reasoning on their mutual positions. The code is available at https://github.com/cantarinigiorgio/HHP-Net.