Class-Aware Fully Convolutional Gaussian and Poisson Denoising

Tal Remez, Or Litany, Raja Giryes, Alex M. Bronstein

Research output: Contribution to journalArticlepeer-review


We propose a fully convolutional neural-network architecture for image denoising which is simple yet powerful. Its structure allows to exploit the gradual nature of the denoising process, in which the shallow layers handle local noise statistics, while deeper layers recover edges and enhance textures. Our method advances the state of the art when trained for different noise levels and distributions (both Gaussian and Poisson). In addition, we show that making the denoiser class-aware by exploiting semantic class information boosts the performance, enhances the textures, and reduces the artifacts.

Original languageEnglish
Article number8418389
Pages (from-to)5707-5722
Number of pages16
JournalIEEE Transactions on Image Processing
Issue number11
StatePublished - Nov 2018


  • Gaussian noise
  • Image denoising
  • Poisson noise
  • class-aware denoising
  • deep learning
  • fully convolutional networks
  • video denoising

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Class-Aware Fully Convolutional Gaussian and Poisson Denoising'. Together they form a unique fingerprint.

Cite this