# Stacked Dense U-Nets with Dual Transformers for Robust Face Alignment

arXiv: https://arxiv.org/abs/1812.01936 · HTML: https://mlsanity.com/paper/1812.01936/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2018.

## Built on by (most cited first, 17 of 17)

- [A Comprehensive Study on Face Recognition Biases Beyond Demographics](https://mlsanity.com/paper/2103.01592/) (2021)
- [MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image](https://mlsanity.com/paper/2112.02753/) (2021)
- [VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention](https://mlsanity.com/paper/2503.15138/) (2025)
- [Pixel-Level Face Image Quality Assessment for Explainable Face Recognition](https://mlsanity.com/paper/2110.11001/) (2021)
- [ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation](https://mlsanity.com/paper/2503.17671/) (2025)
- [VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention](https://mlsanity.com/paper/2412.02259/) (2024)
- [Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study](https://mlsanity.com/paper/2107.12202/) (2021)
- [MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup Transfer](https://mlsanity.com/paper/2408.12312/) (2024)
- [FakeParts: a New Family of AI-Generated DeepFakes](https://mlsanity.com/paper/2508.21052/) (2025)
- [3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs](https://mlsanity.com/paper/2203.04643/) (2022)
- [On the Illusion of Gender Bias in Face Recognition: Explaining the Fairness Issue Through Non-demographic Attributes](https://mlsanity.com/paper/2501.12020/) (2025)
- [Head2HeadFS: Video-based Head Reenactment with Few-shot Learning](https://mlsanity.com/paper/2103.16229/) (2021)
- [LocalEyenet: Deep Attention framework for Localization of Eyes](https://mlsanity.com/paper/2303.12728/) (2023)
- [Face Clustering for Connection Discovery from Event Images](https://mlsanity.com/paper/2309.01092/) (2023)
- [M3DHMR: Monocular 3D Hand Mesh Recovery](https://mlsanity.com/paper/2505.20058/) (2025)
- [SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation](https://mlsanity.com/paper/2510.16396/) (2025)
- [Diff-ID: Identity Consistent Facial Image Generation and Morphing via Diffusion Models](https://mlsanity.com/paper/2607.25078/) (2026)

## Abstract (arXiv)

Facial landmark localisation in images captured in-the-wild is an important and challenging problem. The current state-of-the-art revolves around certain kinds of Deep Convolutional Neural Networks (DCNNs) such as stacked U-Nets and Hourglass networks. In this work, we innovatively propose stacked dense U-Nets for this task. We design a novel scale aggregation network topology structure and a channel aggregation building block to improve the model's capacity without sacrificing the computational complexity and model size. With the assistance of deformable convolutions inside the stacked dense U-Nets and coherent loss for outside data transformation, our model obtains the ability to be spatially invariant to arbitrary input face images. Extensive experiments on many in-the-wild datasets, validate the robustness of the proposed method under extreme poses, exaggerated expressions and heavy occlusions. Finally, we show that accurate 3D face alignment can assist pose-invariant face recognition where we achieve a new state-of-the-art accuracy on CFP-FP.