Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks

Abstract

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

Accepted at TIP 2020

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Smoothed Dilated Convolutions for Improved Dense Prediction
• Multi-style Generative Network for Real-time Transfer

Cited by in corpus (9)

• BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring
• Confidence Measure Guided Single Image De-raining
• Exploring Overcomplete Representations for Single Image Deraining using CNNs
• Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs
• Dense Uncertainty Estimation
• Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos
• Continuous Facial Motion Deblurring
• Network Architecture Search for Face Enhancement
• FineNet: Frame Interpolation and Enhancement for Face Video Deblurring