# Identity-Preserving Pose-Robust Face Hallucination Through Face Subspace Prior

arXiv: https://arxiv.org/abs/2111.10634 · HTML: https://mlsanity.com/paper/2111.10634/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 71 references that are in the map.
- First posted on arXiv 20 Nov 2021.

## Builds on (most cited first, 21 of 21)

- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Deep Back-Projection Networks For Super-Resolution](https://mlsanity.com/paper/1803.02735/) (2018)
- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](https://mlsanity.com/paper/1803.07835/) (2018)
- [Structure-Preserving Super Resolution with Gradient Guidance](https://mlsanity.com/paper/2003.13081/) (2020)
- [To learn image super-resolution, use a GAN to learn how to do image degradation first](https://mlsanity.com/paper/1807.11458/) (2018)
- [HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment](https://mlsanity.com/paper/2005.05005/) (2020)
- [Learning Spatial Attention for Face Super-Resolution](https://mlsanity.com/paper/2012.01211/) (2020)
- [Fast Fusion of Multi-Band Images Based on Solving a Sylvester Equation](https://mlsanity.com/paper/1502.03121/) (2015)
- [Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network](https://mlsanity.com/paper/1707.05425/) (2017)
- [SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination](https://mlsanity.com/paper/1807.08370/) (2018)
- [Fast Single Image Super-Resolution](https://mlsanity.com/paper/1510.00143/) (2015)
- [Face Hallucination using Linear Models of Coupled Sparse Support](https://mlsanity.com/paper/1512.06009/) (2015)
- [Sequential Gating Ensemble Network for Noise Robust Multi-Scale Face Restoration](https://mlsanity.com/paper/1812.11834/) (2018)
- [Context-Patch Face Hallucination Based on Thresholding Locality-constrained Representation and Reproducing Learning](https://mlsanity.com/paper/1809.00665/) (2018)
- [Con-Patch: When a Patch Meets its Context](https://mlsanity.com/paper/1603.06812/) (2016)

## Built on by (most cited first, 1 of 1)

- [Survey on Deep Face Restoration: From Non-blind to Blind and Beyond](https://mlsanity.com/paper/2309.15490/) (2023)

## Abstract (arXiv)

Over the past few decades, numerous attempts have been made to address the problem of recovering a high-resolution (HR) facial image from its corresponding low-resolution (LR) counterpart, a task commonly referred to as face hallucination. Despite the impressive performance achieved by position-patch and deep learning-based methods, most of these techniques are still unable to recover identity-specific features of faces. The former group of algorithms often produces blurry and oversmoothed outputs particularly in the presence of higher levels of degradation, whereas the latter generates faces which sometimes by no means resemble the individuals in the input images. In this paper, a novel face super-resolution approach will be introduced, in which the hallucinated face is forced to lie in a subspace spanned by the available training faces. Therefore, in contrast to the majority of existing face hallucination techniques and thanks to this face subspace prior, the reconstruction is performed in favor of recovering person-specific facial features, rather than merely increasing image quantitative scores. Furthermore, inspired by recent advances in the area of 3D face reconstruction, an efficient 3D dictionary alignment scheme is also presented, through which the algorithm becomes capable of dealing with low-resolution faces taken in uncontrolled conditions. In extensive experiments carried out on several well-known face datasets, the proposed algorithm shows remarkable performance by generating detailed and close to ground truth results which outperform the state-of-the-art face hallucination algorithms by significant margins both in quantitative and qualitative evaluations.