Unsupervised Domain-Specific Deblurring via Disentangled Representations

03/05/2019
by   Boyu Lu, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 5

page 6

page 7

08/02/2018

Diverse Image-to-Image Translation via Disentangled Representations

Image-to-image translation aims to learn the mapping between two visual ...
12/12/2021

Unsupervised Domain-Specific Deblurring using Scale-Specific Attention

In the literature, coarse-to-fine or scale-recurrent approach i.e. progr...
05/02/2019

DRIT++: Diverse Image-to-Image Translation via Disentangled Representations

Image-to-image translation aims to learn the mapping between two visual ...
10/07/2019

ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence

Image degradation due to atmospheric turbulence is common while capturin...
04/26/2021

Clean Images are Hard to Reblur: A New Clue for Deblurring

The goal of dynamic scene deblurring is to remove the motion blur presen...
03/25/2021

Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation

Existing deep learning-based image deraining methods have achieved promi...
05/11/2019

Disentangling Content and Style via Unsupervised Geometry Distillation

It is challenging to disentangle an object into two orthogonal spaces of...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.