# KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressors

arXiv: https://arxiv.org/abs/1702.05085 · HTML: https://mlsanity.com/paper/1702.05085/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2017.

## Built on by (most cited first, 10 of 10)

- [HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty](https://mlsanity.com/paper/2111.01440/) (2021)
- [DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles](https://mlsanity.com/paper/2302.01110/) (2023)
- [LwPosr: Lightweight Efficient Fine-Grained Head Pose Estimation](https://mlsanity.com/paper/2202.03544/) (2022)
- [Regional Attention Network (RAN) for Head Pose and Fine-grained Gesture Recognition](https://mlsanity.com/paper/2101.06634/) (2021)
- [MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation](https://mlsanity.com/paper/2110.10953/) (2021)
- [UET-Headpose: A sensor-based top-view head pose dataset](https://mlsanity.com/paper/2111.07039/) (2021)
- [Simultaneous face detection and 360 degree headpose estimation](https://mlsanity.com/paper/2111.11604/) (2021)
- [HeadPosr: End-to-end Trainable Head Pose Estimation using Transformer Encoders](https://mlsanity.com/paper/2202.03548/) (2022)
- [An Effective Deep Network for Head Pose Estimation without Keypoints](https://mlsanity.com/paper/2210.13705/) (2022)
- [GADS: A Super Lightweight Model for Head Pose Estimation](https://mlsanity.com/paper/2504.15751/) (2025)

## Abstract (arXiv)

Keypoint detection is one of the most important pre-processing steps in tasks such as face modeling, recognition and verification. In this paper, we present an iterative method for Keypoint Estimation and Pose prediction of unconstrained faces by Learning Efficient H-CNN Regressors (KEPLER) for addressing the face alignment problem. Recent state of the art methods have shown improvements in face keypoint detection by employing Convolution Neural Networks (CNNs). Although a simple feed forward neural network can learn the mapping between input and output spaces, it cannot learn the inherent structural dependencies. We present a novel architecture called H-CNN (Heatmap-CNN) which captures structured global and local features and thus favors accurate keypoint detecion. HCNN is jointly trained on the visibility, fiducials and 3D-pose of the face. As the iterations proceed, the error decreases making the gradients small and thus requiring efficient training of DCNNs to mitigate this. KEPLER performs global corrections in pose and fiducials for the first four iterations followed by local corrections in the subsequent stage. As a by-product, KEPLER also provides 3D pose (pitch, yaw and roll) of the face accurately. In this paper, we show that without using any 3D information, KEPLER outperforms state of the art methods for alignment on challenging datasets such as AFW and AFLW.