9
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Deblurring using Analysis-Synthesis Networks Pair

      Preprint
      ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Blind image deblurring remains a challenging problem for modern artificial neural networks. Unlike other image restoration problems, deblurring networks fail behind the performance of existing deblurring algorithms in case of uniform and 3D blur models. This follows from the diverse and profound effect that the unknown blur-kernel has on the deblurring operator. We propose a new architecture which breaks the deblurring network into an analysis network which estimates the blur, and a synthesis network that uses this kernel to deblur the image. Unlike existing deblurring networks, this design allows us to explicitly incorporate the blur-kernel in the network's training. In addition, we introduce new cross-correlation layers that allow better blur estimations, as well as unique components that allow the estimate blur to control the action of the synthesis deblurring action. Evaluating the new approach over established benchmark datasets shows its ability to achieve state-of-the-art deblurring accuracy on various tests, as well as offer a major speedup in runtime.

          Related collections

          Author and article information

          Journal
          06 April 2020
          Article
          2004.02956
          0e63367c-dfcb-46d5-94bb-236ecd89eff2

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          Computer Vision and Pattern Recognition (CVPR) 2020
          cs.CV cs.LG eess.IV

          Computer vision & Pattern recognition,Artificial intelligence,Electrical engineering

          Comments

          Comment on this article