Scale Input Adapted Attention for Image Denoising Using a Densely Connected U-Net: SADE-Net


Acar V., Ekşioğlu E. M.

13th International Conference on Computational Collective Intelligence, ICCCI 2021, Virtual, Online, 29 September - 01 October 2021, vol.12876 LNAI, pp.792-801 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 12876 LNAI
  • Doi Number: 10.1007/978-3-030-88081-1_60
  • City: Virtual, Online
  • Page Numbers: pp.792-801
  • Keywords: Convolutional Neural Networks, Deep learning, Image denoising
  • Istanbul Technical University Affiliated: Yes

Abstract

© 2021, Springer Nature Switzerland AG.In this work, we address the problem of image denoising using deep neural networks. Recent developments in convolutional neural networks provide a very potent alternative for image restoration applications and in particular for image denoising. A particularly popular deep network structure for image processing are the auto-encoders which include the U-Net as an important example. U-Nets contract and expand feature maps repeatedly, which leads to extraction of multi scale information as well as an increase in the effective receptive field when compared to conventional convolutional nets. In this paper, we propose the integration of a multi scale channel attention module through a U-Net structure as a novelty for the image denoising problem. The introduced network structure also utilizes multi scale inputs in the various substages of the encoder module in a novel manner. Simulation results demonstrate competitive and mostly superior performance when compared to some state of the art deep learning based image denoising methodologies. Qualitative results also indicate that the developed deep network framework has powerful detail preserving capability.