BP-DIP: A backprojection based deep image prior

Jenny Zukerman, Tom Tirer, Raja Giryes

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Deep neural networks are a very powerful tool for many computer vision tasks, including image restoration, exhibiting state-of-the-art results. However, the performance of deep learning methods tends to drop once the observation model used in training mismatches the one in test time. In addition, most deep learning methods require vast amounts of training data, which are not accessible in many applications. To mitigate these disadvantages, we propose to combine two image restoration approaches: (i) Deep Image Prior (DIP), which trains a convolutional neural network (CNN) from scratch in test time using the given degraded image. It does not require any training data and builds on the implicit prior imposed by the CNN architecture; and (ii) a backprojection (BP) fidelity term, which is an alternative to the standard least squares loss that is usually used in previous DIP works. We demonstrate the performance of the proposed method, termed BP-DIP, on the deblurring task and show its advantages over the plain DIP, with both higher PSNR values and better inference run-time.

Original languageEnglish
Title of host publication28th European Signal Processing Conference, EUSIPCO 2020 - Proceedings
PublisherEuropean Signal Processing Conference, EUSIPCO
Number of pages5
ISBN (Electronic)9789082797053
StatePublished - 24 Jan 2021
Event28th European Signal Processing Conference, EUSIPCO 2020 - Amsterdam, Netherlands
Duration: 24 Aug 202028 Aug 2020

Publication series

NameEuropean Signal Processing Conference
ISSN (Print)2219-5491


Conference28th European Signal Processing Conference, EUSIPCO 2020


  • Deep learning
  • Image deblurring
  • Loss functions


Dive into the research topics of 'BP-DIP: A backprojection based deep image prior'. Together they form a unique fingerprint.

Cite this