# FacePoseNet: Making a Case for Landmark-Free Face Alignment

arXiv: https://arxiv.org/abs/1708.07517 · HTML: https://mlsanity.com/paper/1708.07517/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2017.

## Built on by (most cited first, 21 of 21)

- [HyperInverter: Improving StyleGAN Inversion via Hypernetwork](https://mlsanity.com/paper/2112.00719/) (2021)
- [DiffFace: Diffusion-based Face Swapping with Facial Guidance](https://mlsanity.com/paper/2212.13344/) (2022)
- [FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/2202.12972/) (2022)
- [REALY: Rethinking the Evaluation of 3D Face Reconstruction](https://mlsanity.com/paper/2203.09729/) (2022)
- [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)
- [HRAvatar: High-Quality and Relightable Gaussian Head Avatar](https://mlsanity.com/paper/2503.08224/) (2025)
- [Multi-task head pose estimation in-the-wild](https://mlsanity.com/paper/2202.02299/) (2022)
- [Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation](https://mlsanity.com/paper/2309.07654/) (2023)
- [Sparse to Dense Dynamic 3D Facial Expression Generation](https://mlsanity.com/paper/2105.07463/) (2021)
- [Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Image](https://mlsanity.com/paper/2205.04126/) (2022)
- [Generating Multiple 4D Expression Transitions by Learning Face Landmark Trajectories](https://mlsanity.com/paper/2208.00050/) (2022)
- [Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian](https://mlsanity.com/paper/2208.09122/) (2022)
- [EFHQ: Multi-purpose ExtremePose-Face-HQ dataset](https://mlsanity.com/paper/2312.17205/) (2023)
- [LwPosr: Lightweight Efficient Fine-Grained Head Pose Estimation](https://mlsanity.com/paper/2202.03544/) (2022)
- [LSF-Animation: Label-Free Speech-Driven Facial Animation via Implicit Feature Representation](https://mlsanity.com/paper/2510.21864/) (2025)
- [MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance](https://mlsanity.com/paper/2101.09899/) (2021)
- [SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning](https://mlsanity.com/paper/2110.10842/) (2021)
- [Face Deblurring Based on Separable Normalization and Adaptive Denormalization](https://mlsanity.com/paper/2112.09833/) (2021)
- [An Effective Deep Network for Head Pose Estimation without Keypoints](https://mlsanity.com/paper/2210.13705/) (2022)
- [Boosting of Head Pose Estimation by Knowledge Distillation](https://mlsanity.com/paper/2108.09183/) (2021)
- [3D Face Reconstruction From Radar Images](https://mlsanity.com/paper/2412.02403/) (2024)

## Abstract (arXiv)

We show how a simple convolutional neural network (CNN) can be trained to accurately and robustly regress 6 degrees of freedom (6DoF) 3D head pose, directly from image intensities. We further explain how this FacePoseNet (FPN) can be used to align faces in 2D and 3D as an alternative to explicit facial landmark detection for these tasks. We claim that in many cases the standard means of measuring landmark detector accuracy can be misleading when comparing different face alignments. Instead, we compare our FPN with existing methods by evaluating how they affect face recognition accuracy on the IJB-A and IJB-B benchmarks: using the same recognition pipeline, but varying the face alignment method. Our results show that (a) better landmark detection accuracy measured on the 300W benchmark does not necessarily imply better face recognition accuracy. (b) Our FPN provides superior 2D and 3D face alignment on both benchmarks. Finally, (c), FPN aligns faces at a small fraction of the computational cost of comparably accurate landmark detectors. For many purposes, FPN is thus a far faster and far more accurate face alignment method than using facial landmark detectors.