BROWSE

Related Researcher

Author

Yang, Seungjoon
Signal Processing Lab (SPL)
Research Interests
  • Statistical signal processing, multi-rate systems, image/video processing, computer vision

ITEM VIEW & DOWNLOAD

Non-stationary Deep Network for Restoration of Non-Stationary Lens Blur

Cited 0 times inthomson ciCited 0 times inthomson ci
Title
Non-stationary Deep Network for Restoration of Non-Stationary Lens Blur
Author
Kim, SoowoongGwak, MoonsungYang, Seungjoon
Keywords
Deep learning; Restoration; Non-stationary blur; Lens blur
Issue Date
201806
Publisher
ELSEVIER SCIENCE BV
Citation
PATTERN RECOGNITION LETTERS, v.108, no., pp.62 - 69
Abstract
Optical aberrations of a lens introduce lens blur to photographed images. Lens blur is non-stationary with the amount and characteristics of blur varying depending on spatial pixel locations in an image. This work presents non-stationary deep networks for the restoration of non-stationary lens blur. Deep networks have relatively larger receptive fields. However, the receptive fields of stationary deep networks are not wide enough for the networks to cope with the non-stationarity of lens blur that span the entire image. We use spatial pixel locations as an additional input to networks to let the network utilize location dependent features to handle the non-stationarity. Experimental results show that even shallower non-stationary networks provide better performance than deeper stationary networks. The non-stationary networks are trained from pairs of images photographed at different aperture settings, eliminating the necessity of estimation or measurement of pixel-wise variant non-stationary lens blur.
URI
Go to Link
DOI
http://dx.doi.org/10.1016/j.patrec.2018.03.001
ISSN
0167-8655
Appears in Collections:
ECE_Journal Papers
Files in This Item:
There are no files associated with this item.

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qr_code

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU