Learning to Deblur

We describe a learning-based approach to blind image deconvolution. It uses a deep layered architecture, parts of which are borrowed from recent work on neural network learning, and parts of which incorporate computations that are specific to image deconvolution. The system is trained end-to-end on...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on pattern analysis and machine intelligence Vol. 38; no. 7; pp. 1439 - 1451
Main Authors Schuler, Christian J., Hirsch, Michael, Harmeling, Stefan, Scholkopf, Bernhard
Format Journal Article
LanguageEnglish
Published United States IEEE 01.07.2016
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Artificial neural networks
Convolution
Deconvolution
Estimation
Feature extraction
Kernel
machine learning
neural networks
Sharpening and deblurring
Training
machine learning
Sharpening and deblurring
neural networks
Online AccessGet full text

Cover

More Information
Summary:We describe a learning-based approach to blind image deconvolution. It uses a deep layered architecture, parts of which are borrowed from recent work on neural network learning, and parts of which incorporate computations that are specific to image deconvolution. The system is trained end-to-end on a set of artificially generated training examples, enabling competitive performance in blind deconvolution, both with respect to quality and runtime.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2015.2481418