DeepDeblur: Fast one-step blurry face images restoration
This addresses the need for efficient and accurate deblurring in face image applications, though it is incremental as it builds on existing deep learning approaches.
The paper tackles the problem of slow and ineffective restoration of blurry face images by proposing a fast one-step method using a Convolutional Neural Network, achieving state-of-the-art results for small images and improving face recognition accuracy with over 100 times speed increase.
We propose a very fast and effective one-step restoring method for blurry face images. In the last decades, many blind deblurring algorithms have been proposed to restore latent sharp images. However, these algorithms run slowly because of involving two steps: kernel estimation and following non-blind deconvolution or latent image estimation. Also they cannot handle face images in small size. Our proposed method restores sharp face images directly in one step using Convolutional Neural Network. Unlike previous deep learning involved methods that can only handle a single blur kernel at one time, our network is trained on totally random and numerous training sample pairs to deal with the variances due to different blur kernels in practice. A smoothness regularization as well as a facial regularization are added to keep facial identity information which is the key to face image applications. Comprehensive experiments demonstrate that our proposed method can handle various blur kenels and achieve state-of-the-art results for small size blurry face images restoration. Moreover, the proposed method shows significant improvement in face recognition accuracy along with increasing running speed by more than 100 times.