Unsupervised Domain-Specific Deblurring via Disentangled Representations

Abstract

Image deblurring aims to restore the latent sharp images from the corresponding blurred ones. In this paper, we present an unsupervised method for domain-specific single-image deblurring based on disentangled representations. The disentanglement is achieved by splitting the content and blur features in a blurred image using content encoders and blur encoders. We enforce a KL divergence loss to regularize the distribution range of extracted blur attributes such that little content information is contained. Meanwhile, to handle the unpaired training data, a blurring branch and the cycle-consistency loss are added to guarantee that the content structures of the deblurred results match the original images. We also add an adversarial loss on deblurred results to generate visually realistic images and a perceptual loss to further mitigate the artifacts. We perform extensive experiments on the tasks of face and text deblurring using both synthetic datasets and real images, and achieve improved results compared to recent state-of-the-art deblurring methods.

Accepted by CVPR 2019. Code is released at: https://github.com/ustclby/Unsupervised-Domain-Specific-Deblurring/

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Cross-Domain Image Generation
• Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
• An Experimental Evaluation of Covariates Effects on Unconstrained Face Verification

Cited by in corpus (4)

• ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence
• DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking
• Unsupervised Multi-Domain Multimodal Image-to-Image Translation with Explicit Domain-Constrained Disentanglement
• Domain Fingerprints for No-reference Image Quality Assessment