# An Intuitive and Unconstrained 2D Cube Representation for Simultaneous Head Detection and Pose Estimation

arXiv: https://arxiv.org/abs/2212.03623 · HTML: https://mlsanity.com/paper/2212.03623/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 15 of 15)

- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (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)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Real-Time Seamless Single Shot 6D Object Pose Prediction](https://mlsanity.com/paper/1711.08848/) (2017)
- [Fine-Grained Head Pose Estimation Without Keypoints](https://mlsanity.com/paper/1710.00925/) (2017)
- [OnePose: One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2205.12257/) (2022)
- [Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations](https://mlsanity.com/paper/2012.09988/) (2020)
- [Delving Deeper into Convolutional Networks for Learning Video Representations](https://mlsanity.com/paper/1511.06432/) (2015)
- [HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition](https://mlsanity.com/paper/1603.01249/) (2016)
- [6D Rotation Representation For Unconstrained Head Pose Estimation](https://mlsanity.com/paper/2202.12555/) (2022)
- [img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation](https://mlsanity.com/paper/2012.07791/) (2020)
- [WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose](https://mlsanity.com/paper/2005.10353/) (2020)
- [A Vector-based Representation to Enhance Head Pose Estimation](https://mlsanity.com/paper/2010.07184/) (2020)
- [DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image](https://mlsanity.com/paper/2204.03688/) (2022)
- [Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation](https://mlsanity.com/paper/2011.14589/) (2020)

## Built on by (most cited first, 2 of 2)

- [DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles](https://mlsanity.com/paper/2302.01110/) (2023)
- [On the power of data augmentation for head pose estimation](https://mlsanity.com/paper/2407.05357/) (2024)

## Abstract (arXiv)

Most recent head pose estimation (HPE) methods are dominated by the Euler angle representation. To avoid its inherent ambiguity problem of rotation labels, alternative quaternion-based and vector-based representations are introduced. However, they both are not visually intuitive, and often derived from equivocal Euler angle labels. In this paper, we present a novel single-stage keypoint-based method via an it intuitive and it unconstrained 2D cube representation for joint head detection and pose estimation. The 2D cube is an orthogonal projection of the 3D regular hexahedron label roughly surrounding one head, and itself contains the head location. It can reflect the head orientation straightforwardly and unambiguously in any rotation angle. Unlike the general 6-DoF object pose estimation, our 2D cube ignores the 3-DoF of head size but retains the 3-DoF of head pose. Based on the prior of equal side length, we can effortlessly obtain the closed-form solution of Euler angles from predicted 2D head cube instead of applying the error-prone PnP algorithm. In experiments, our proposed method achieves comparable results with other representative methods on the public AFLW2000 and BIWI datasets. Besides, a novel test on the CMU panoptic dataset shows that our method can be seamlessly adapted to the unconstrained full-view HPE task without modification.