# Towards Large-Scale Pose-Invariant Face Recognition Using Face Defrontalization

arXiv: https://arxiv.org/abs/2506.04496 · HTML: https://mlsanity.com/paper/2506.04496/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 62 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [Range Loss for Deep Face Recognition with Long-tail](https://mlsanity.com/paper/1611.08976/) (2016)
- [SynFace: Face Recognition with Synthetic Data](https://mlsanity.com/paper/2108.07960/) (2021)
- [Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis](https://mlsanity.com/paper/1704.04086/) (2017)
- [UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition](https://mlsanity.com/paper/1712.04695/) (2017)
- [Towards Large-Pose Face Frontalization in the Wild](https://mlsanity.com/paper/1704.06244/) (2017)
- [Effective Face Frontalization in Unconstrained Images](https://mlsanity.com/paper/1411.7964/) (2014)
- [Pose-Robust Face Recognition via Deep Residual Equivariant Mapping](https://mlsanity.com/paper/1803.00839/) (2018)
- [Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition](https://mlsanity.com/paper/1702.04710/) (2017)
- [Dual-Attention GAN for Large-Pose Face Frontalization](https://mlsanity.com/paper/2002.07227/) (2020)
- [Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision](https://mlsanity.com/paper/2008.06843/) (2020)
- [Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization](https://mlsanity.com/paper/1806.08472/) (2018)

## Abstract (arXiv)

Face recognition under extreme head poses is a challenging task. Ideally, a face recognition system should perform well across different head poses, which is known as pose-invariant face recognition. To achieve pose invariance, current approaches rely on sophisticated methods, such as face frontalization and various facial feature extraction model architectures. However, these methods are somewhat impractical in real-life settings and are typically evaluated on small scientific datasets, such as Multi-PIE. In this work, we propose the inverse method of face frontalization, called face defrontalization, to augment the training dataset of facial feature extraction model. The method does not introduce any time overhead during the inference step. The method is composed of: 1) training an adapted face defrontalization FFWM model on a frontal-profile pairs dataset, which has been preprocessed using our proposed face alignment method; 2) training a ResNet-50 facial feature extraction model based on ArcFace loss on a raw and randomly defrontalized large-scale dataset, where defrontalization was performed with our previously trained face defrontalization model. Our method was compared with the existing approaches on four open-access datasets: LFW, AgeDB, CFP, and Multi-PIE. Defrontalization shows improved results compared to models without defrontalization, while the proposed adjustments show clear superiority over the state-of-the-art face frontalization FFWM method on three larger open-access datasets, but not on the small Multi-PIE dataset for extreme poses (75 and 90 degrees). The results suggest that at least some of the current methods may be overfitted to small datasets.