arXiv Open Access 2019

Unsupervised Domain-Specific Deblurring via Disentangled Representations

Boyu Lu Jun-Cheng Chen Rama Chellappa
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (3)

B

Boyu Lu

J

Jun-Cheng Chen

R

Rama Chellappa

Format Sitasi

Lu, B., Chen, J., Chellappa, R. (2019). Unsupervised Domain-Specific Deblurring via Disentangled Representations. https://arxiv.org/abs/1903.01594

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2019
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓