Image Denoising Using Deep Convolutional Autoencoder with Feature Pyramids

Published:

Published In: Turkish Journal of Electrical Engineering & Computer Sciences (TBA)
Journal Website: https://journals.tubitak.gov.tr/elektrik

Ekrem Çetinkaya (Ozyegin University, Istanbul, Turkey / Alpen-Adria-Universität Klagenfurt, Klagenfurt, Austria) and M. Furkan Kıraç (Ozyegin University, Istanbul, Turkey)

Abstract: Image denoising is one of the fundamental problems in the image processing field since it is the preliminary step for many computer vision applications. Various approaches have been used for image denoising throughout the years from spatial filtering to model-based approaches. Having outperformed all traditional methods, neural-network-based discriminative methods have gained popularity in recent years. However, most of these methods still struggle to achieve flexibility against various noise levels and types. In this paper, a deep convolutional autoencoder combined with a variant of feature pyramid network is proposed for image denoising. Simulated data generated by Blender software along with corrupted natural images are used during training to improve robustness against various noise levels. Experimental results show that the proposed method can achieve competitive performance in blind Gaussian denoising with significantly less training time required compared to state-of-the-art methods. Extensive experiments showed the proposed method gives promising performance in a wide range of noise levels with a single network.

Keywords: Image Denoising, Convolutional Neural Network, Autoencoder, Feature Pyramid

Citation:

@article{cetinkaya2020denoising,
  title={Image denoising using deep convolutional autoencoder with feature pyramids},
  author={Cetinkaya, Ekrem and Kirac, M. Furkan},
  journal={Turkish Journal of Electrical Engineering \& Computer Sciences},
  volume={28},
  number={4},
  pages={2096-2109},
  year={2020},
  publisher={The Scientific and Technological Research Council of Turkey}
}

Download Paper Here

Paper Link to Journal