# Masked Face Inpainting Through Residual Attention UNet

arXiv: https://arxiv.org/abs/2209.08850 · HTML: https://mlsanity.com/paper/2209.08850/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 19 Sep 2022.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [Pluralistic Image Completion](https://mlsanity.com/paper/1903.04227/) (2019)
- [Masked Face Recognition for Secure Authentication](https://mlsanity.com/paper/2008.11104/) (2020)
- [VCNet: A Robust Approach to Blind Image Inpainting](https://mlsanity.com/paper/2003.06816/) (2020)
- [Faster Unsupervised Semantic Inpainting: A GAN Based Approach](https://mlsanity.com/paper/1908.04968/) (2019)

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

- [PHAF-Personalized Hand Avatars in a Flash](https://mlsanity.com/paper/2606.03420/) (2026)

## Abstract (arXiv)

Realistic image restoration with high texture areas such as removing face masks is challenging. The state-of-the-art deep learning-based methods fail to guarantee high-fidelity, cause training instability due to vanishing gradient problems (e.g., weights are updated slightly in initial layers) and spatial information loss. They also depend on intermediary stage such as segmentation meaning require external mask. This paper proposes a blind mask face inpainting method using residual attention UNet to remove the face mask and restore the face with fine details while minimizing the gap with the ground truth face structure. A residual block feeds info to the next layer and directly into the layers about two hops away to solve the gradient vanishing problem. Besides, the attention unit helps the model focus on the relevant mask region, reducing resources and making the model faster. Extensive experiments on the publicly available CelebA dataset show the feasibility and robustness of our proposed model. Code is available at urlhttps://github.com/mdhosen/Mask-Face-Inpainting-Using-Residual-Attention-Unet