# Deep Alignment Network: A convolutional neural network for robust face alignment

arXiv: https://arxiv.org/abs/1706.01789 · HTML: https://mlsanity.com/paper/1706.01789/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2017.

## Built on by (most cited first, 30 of 44)

- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark](https://mlsanity.com/paper/2104.12668/) (2021)
- [Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning](https://mlsanity.com/paper/2203.06541/) (2022)
- [Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species](https://mlsanity.com/paper/2112.06183/) (2021)
- [A Large-Scale, Time-Synchronized Visible and Thermal Face Dataset](https://mlsanity.com/paper/2101.02637/) (2021)
- [ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2208.11547/) (2022)
- [Shape Preserving Facial Landmarks with Graph Attention Networks](https://mlsanity.com/paper/2210.07233/) (2022)
- [Face2PPG: An unsupervised pipeline for blood volume pulse extraction from faces](https://mlsanity.com/paper/2202.04101/) (2022)
- [HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap](https://mlsanity.com/paper/2104.03100/) (2021)
- [Subpixel Heatmap Regression for Facial Landmark Localization](https://mlsanity.com/paper/2111.02360/) (2021)
- [A Review of Deep Learning-based Approaches for Deepfake Content Detection](https://mlsanity.com/paper/2202.06095/) (2022)
- [An End-to-End Review of Gaze Estimation and its Interactive Applications on Handheld Mobile Devices](https://mlsanity.com/paper/2307.00122/) (2023)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [Face-MLLM: A Large Face Perception Model](https://mlsanity.com/paper/2410.20717/) (2024)
- [FaceShot: Bring Any Character into Life](https://mlsanity.com/paper/2503.00740/) (2025)
- [ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation](https://mlsanity.com/paper/2103.00119/) (2021)
- [Depression Recognition using Remote Photoplethysmography from Facial Videos](https://mlsanity.com/paper/2206.04399/) (2022)
- [What's in a Decade? Transforming Faces Through Time](https://mlsanity.com/paper/2210.06642/) (2022)
- [IntereStyle: Encoding an Interest Region for Robust StyleGAN Inversion](https://mlsanity.com/paper/2209.10811/) (2022)
- [A Synthesis-Based Approach for Thermal-to-Visible Face Verification](https://mlsanity.com/paper/2108.09558/) (2021)
- [T-FAKE: Synthesizing Thermal Images for Facial Landmarking](https://mlsanity.com/paper/2408.15127/) (2024)
- [LOTR: Face Landmark Localization Using Localization Transformer](https://mlsanity.com/paper/2109.10057/) (2021)
- [Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks](https://mlsanity.com/paper/2111.07047/) (2021)
- [Generalizable Face Landmarking Guided by Conditional Face Warping](https://mlsanity.com/paper/2404.12322/) (2024)
- [Label Encoding for Regression Networks](https://mlsanity.com/paper/2212.01927/) (2022)
- [Point detection through multi-instance deep heatmap regression for sutures in endoscopy](https://mlsanity.com/paper/2111.08468/) (2021)
- [ArtFacePoints: High-resolution Facial Landmark Detection in Paintings and Prints](https://mlsanity.com/paper/2210.09204/) (2022)
- [ABN: Anti-Blur Neural Networks for Multi-Stage Deformable Image Registration](https://mlsanity.com/paper/2212.03277/) (2022)
- [Multi-Domain Multi-Definition Landmark Localization for Small Datasets](https://mlsanity.com/paper/2203.10358/) (2022)
- [Learning Label Encodings for Deep Regression](https://mlsanity.com/paper/2303.02273/) (2023)

## Abstract (arXiv)

In this paper, we propose Deep Alignment Network (DAN), a robust face alignment method based on a deep neural network architecture. DAN consists of multiple stages, where each stage improves the locations of the facial landmarks estimated by the previous stage. Our method uses entire face images at all stages, contrary to the recently proposed face alignment methods that rely on local patches. This is possible thanks to the use of landmark heatmaps which provide visual information about landmark locations estimated at the previous stages of the algorithm. The use of entire face images rather than patches allows DAN to handle face images with large variation in head pose and difficult initializations. An extensive evaluation on two publicly available datasets shows that DAN reduces the state-of-the-art failure rate by up to 70%. Our method has also been submitted for evaluation as part of the Menpo challenge.