Bm3d Vs 2-Layer Onn

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


Despite their recent success on image denoising, the need for deep and complex architectures still hinders the practical usage of CNNs. Older but computationally more efficient methods such as BM3D remain a popular choice, especially in resource-constrained scenarios. In this study, we aim to find out whether compact neural networks can learn to produce competitive results as compared to BM3D for AWGN image denoising. To this end, we conFigure networks with only two hidden layers and employ different neuron models and layer widths for comparing the performance with BM3D across different AWGN noise levels. Our results conclusively show that the recently proposed self-organized variant of operational neural networks based on a generative neuron model (Self-ONNs) is not only a better choice as compared to CNNs, but also provide competitive results as compared to BM3D and even significantly surpass it for high noise levels.
Original languageEnglish
Title of host publication2021 IEEE International Conference on Image Processing (ICIP)
Number of pages5
ISBN (Electronic)978-1-6654-4115-5
Publication statusPublished - 2021
Publication typeA4 Article in a conference publication
EventIEEE International Conference on Image Processing - , United States
Duration: 19 Sep 202122 Sep 2021

Publication series

NameProceedings : International Conference on Image Processing
ISSN (Electronic)2381-8549


ConferenceIEEE International Conference on Image Processing
Country/TerritoryUnited States


  • AWGN
  • Conferences
  • Neurons
  • Computer architecture
  • Computational efficiency
  • Convolutional neural networks
  • Biological neural networks
  • Image denoising
  • operational neural networks
  • self-organized operational neural networks
  • discriminative learning

Publication forum classification

  • Publication forum level 1


Dive into the research topics of 'Bm3d Vs 2-Layer Onn'. Together they form a unique fingerprint.

Cite this