# Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks

arXiv: https://arxiv.org/abs/1907.13106 · HTML: https://mlsanity.com/paper/1907.13106/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2019.

## Built on by (most cited first, 24 of 24)

- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Explore Image Deblurring via Blur Kernel Space](https://mlsanity.com/paper/2104.00317/) (2021)
- [BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring](https://mlsanity.com/paper/2101.07518/) (2021)
- [Learning to restore images degraded by atmospheric turbulence using uncertainty](https://mlsanity.com/paper/2207.03447/) (2022)
- [Face Deblurring using Dual Camera Fusion on Mobile Phones](https://mlsanity.com/paper/2207.11617/) (2022)
- [Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond](https://mlsanity.com/paper/2307.08996/) (2023)
- [Survey on Deep Face Restoration: From Non-blind to Blind and Beyond](https://mlsanity.com/paper/2309.15490/) (2023)
- [Deep Face Restoration: A Survey](https://mlsanity.com/paper/2211.02831/) (2022)
- [MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection](https://mlsanity.com/paper/2307.02733/) (2023)
- [Dense Uncertainty Estimation](https://mlsanity.com/paper/2110.06427/) (2021)
- [RoCA: Robust Cross-Domain End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.10145/) (2025)
- [Priors in Deep Image Restoration and Enhancement: A Survey](https://mlsanity.com/paper/2206.02070/) (2022)
- [Network Architecture Search for Face Enhancement](https://mlsanity.com/paper/2105.06528/) (2021)
- [A survey on facial image deblurring](https://mlsanity.com/paper/2302.05017/) (2023)
- [Towards Unsupervised Blind Face Restoration using Diffusion Prior](https://mlsanity.com/paper/2410.04618/) (2024)
- [Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos](https://mlsanity.com/paper/2410.11828/) (2024)
- [Learning to Deblur and Rotate Motion-Blurred Faces](https://mlsanity.com/paper/2112.07599/) (2021)
- [Face Deblurring Based on Separable Normalization and Adaptive Denormalization](https://mlsanity.com/paper/2112.09833/) (2021)
- [Take a Prior from Other Tasks for Severe Blur Removal](https://mlsanity.com/paper/2302.06898/) (2023)
- [FineNet: Frame Interpolation and Enhancement for Face Video Deblurring](https://mlsanity.com/paper/2103.00871/) (2021)
- [Continuous Facial Motion Deblurring](https://mlsanity.com/paper/2207.06626/) (2022)
- [Forbes: Face Obfuscation Rendering via Backpropagation Refinement Scheme](https://mlsanity.com/paper/2407.14170/) (2024)
- [CodeFormer++: Blind Face Restoration Using Deformable Registration and Deep Metric Learning](https://mlsanity.com/paper/2510.04410/) (2025)
- [FADRA: Frequency-Aware Diffusion with Residual Adaptation for Video Face Restoration](https://mlsanity.com/paper/2607.06389/) (2026)

## Abstract (arXiv)

We propose a novel multi-stream architecture and training methodology that exploits semantic labels for facial image deblurring. The proposed Uncertainty Guided Multi- Stream Semantic Network (UMSN) processes regions belonging to each semantic class independently and learns to combine their outputs into the final deblurred result. Pixel-wise semantic labels are obtained using a segmentation network. A predicted confidence measure is used during training to guide the network towards the challenging regions of the human face such as the eyes and nose. The entire network is trained in an end- to-end fashion. Comprehensive experiments on three different face datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art face deblurring methods. Code is available at: https://github.com/ rajeevyasarla/UMSN-Face-Deblurring