# Dual-Attention GAN for Large-Pose Face Frontalization

arXiv: https://arxiv.org/abs/2002.07227 · HTML: https://mlsanity.com/paper/2002.07227/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2020.

## Built on by (most cited first, 13 of 13)

- [NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-shot Real Image Animation](https://mlsanity.com/paper/2211.17235/) (2022)
- [BareSkinNet: De-makeup and De-lighting via 3D Face Reconstruction](https://mlsanity.com/paper/2209.09029/) (2022)
- [A Synthesis-Based Approach for Thermal-to-Visible Face Verification](https://mlsanity.com/paper/2108.09558/) (2021)
- [Heterogeneous Face Frontalization via Domain Agnostic Learning](https://mlsanity.com/paper/2107.08311/) (2021)
- [Expression-preserving face frontalization improves visually assisted speech processing](https://mlsanity.com/paper/2204.02810/) (2022)
- [A Brief Survey on Person Recognition at a Distance](https://mlsanity.com/paper/2212.08969/) (2022)
- [The impact of removing head movements on audio-visual speech enhancement](https://mlsanity.com/paper/2202.00538/) (2022)
- [A comprehensive survey on semantic facial attribute editing using generative adversarial networks](https://mlsanity.com/paper/2205.10587/) (2022)
- [Pose Attention-Guided Profile-to-Frontal Face Recognition](https://mlsanity.com/paper/2209.07001/) (2022)
- [Learning Domain and Pose Invariance for Thermal-to-Visible Face Recognition](https://mlsanity.com/paper/2211.09350/) (2022)
- [Test-Time Augmentation for Pose-invariant Face Recognition](https://mlsanity.com/paper/2505.09256/) (2025)
- [Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space](https://mlsanity.com/paper/2108.10265/) (2021)
- [Towards Large-Scale Pose-Invariant Face Recognition Using Face Defrontalization](https://mlsanity.com/paper/2506.04496/) (2025)

## Abstract (arXiv)

Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario. Despite recent advances in deep learning-based face synthesis approaches, this problem is still challenging due to significant pose and illumination discrepancy. In this paper, we present a novel Dual-Attention Generative Adversarial Network (DA-GAN) for photo-realistic face frontalization by capturing both contextual dependencies and local consistency during GAN training. Specifically, a self-attention-based generator is introduced to integrate local features with their long-range dependencies yielding better feature representations, and hence generate faces that preserve identities better, especially for larger pose angles. Moreover, a novel face-attention-based discriminator is applied to emphasize local features of face regions, and hence reinforce the realism of synthetic frontal faces. Guided by semantic segmentation, four independent discriminators are used to distinguish between different aspects of a face (ie skin, keypoints, hairline, and frontalized face). By introducing these two complementary attention mechanisms in generator and discriminator separately, we can learn a richer feature representation and generate identity preserving inference of frontal views with much finer details (i.e., more accurate facial appearance and textures) comparing to the state-of-the-art. Quantitative and qualitative experimental results demonstrate the effectiveness and efficiency of our DA-GAN approach.