Deep Semantic Face Deblurring

Abstract

In this paper, we present an effective and efficient face deblurring algorithm by exploiting semantic cues via deep convolutional neural networks (CNNs). As face images are highly structured and share several key semantic components (e.g., eyes and mouths), the semantic information of a face provides a strong prior for restoration. As such, we propose to incorporate global semantic priors as input and impose local structure losses to regularize the output within a multi-scale deep CNN. We train the network with perceptual and adversarial losses to generate photo-realistic results and develop an incremental training strategy to handle random blur kernels in the wild. Quantitative and qualitative evaluations demonstrate that the proposed face deblurring algorithm restores sharp images with more facial details and performs favorably against state-of-the-art methods in terms of restoration quality, face recognition and execution speed.

arXiv commentThis work is accepted in CVPR 2018. The project website is on https://sites.google.com/site/ziyishenmi/cvpr18_face_deblur

References in corpus (8)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• MatConvNet - Convolutional Neural Networks for MATLAB
• Texture Synthesis Using Convolutional Neural Networks
• Deep Learning Face Attributes in the Wild
• A Neural Approach to Blind Motion Deblurring
• Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
• Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution

Cited by in corpus (4)

• Face Recognition in Low Quality Images: A Survey
• Segmentation-Aware Image Denoising without Knowing True Segmentation
• Face Image Reflection Removal
• FineNet: Frame Interpolation and Enhancement for Face Video Deblurring