# Deep Face Deblurring

arXiv: https://arxiv.org/abs/1704.08772 · HTML: https://mlsanity.com/paper/1704.08772/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2017.

## Built on by (most cited first, 10 of 10)

- [Learning Dual Memory Dictionaries for Blind Face Restoration](https://mlsanity.com/paper/2210.08160/) (2022)
- [Survey on Deep Face Restoration: From Non-blind to Blind and Beyond](https://mlsanity.com/paper/2309.15490/) (2023)
- [From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution](https://mlsanity.com/paper/2210.00752/) (2022)
- [Multi-modality Deep Restoration of Extremely Compressed Face Videos](https://mlsanity.com/paper/2107.05548/) (2021)
- [Median Pixel Difference Convolutional Network for Robust Face Recognition](https://mlsanity.com/paper/2205.15867/) (2022)
- [A survey on facial image deblurring](https://mlsanity.com/paper/2302.05017/) (2023)
- [Learning to Deblur and Rotate Motion-Blurred Faces](https://mlsanity.com/paper/2112.07599/) (2021)
- [Effective Adapter for Face Recognition in the Wild](https://mlsanity.com/paper/2312.01734/) (2023)
- [Unsupervised Domain-Specific Deblurring using Scale-Specific Attention](https://mlsanity.com/paper/2112.06175/) (2021)
- [Continuous Facial Motion Deblurring](https://mlsanity.com/paper/2207.06626/) (2022)

## Abstract (arXiv)

Blind deblurring consists a long studied task, however the outcomes of generic methods are not effective in real world blurred images. Domain-specific methods for deblurring targeted object categories, e.g. text or faces, frequently outperform their generic counterparts, hence they are attracting an increasing amount of attention. In this work, we develop such a domain-specific method to tackle deblurring of human faces, henceforth referred to as face deblurring. Studying faces is of tremendous significance in computer vision, however face deblurring has yet to demonstrate some convincing results. This can be partly attributed to the combination of i) poor texture and ii) highly structure shape that yield the contour/gradient priors (that are typically used) sub-optimal. In our work instead of making assumptions over the prior, we adopt a learning approach by inserting weak supervision that exploits the well-documented structure of the face. Namely, we utilise a deep network to perform the deblurring and employ a face alignment technique to pre-process each face. We additionally surpass the requirement of the deep network for thousands training samples, by introducing an efficient framework that allows the generation of a large dataset. We utilised this framework to create 2MF2, a dataset of over two million frames. We conducted experiments with real world blurred facial images and report that our method returns a result close to the sharp natural latent image.