Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise (AWGN) at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks such as Gaussian denoising, single image super-resolution and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.

References in zbMATH (referenced in 45 articles )

Showing results 1 to 20 of 45.
Sorted by year (citations)

1 2 3 next

  1. Fan, Linwei; Li, Huiyu; Shi, Miaowen; Hua, Zhen; Zhang, Caiming: Two-stage image denoising via an enhanced low-rank prior (2022)
  2. Hou, Ruizhi; Li, Fang: IDPCNN: iterative denoising and projecting CNN for MRI reconstruction (2022)
  3. Lv, Xiao-Guang; Li, Fang; Liu, Jun; Lu, Sheng-Tai: A patch-based low-rank minimization approach for speckle noise reduction in ultrasound images (2022)
  4. Bungert, Leon; Hait-Fraenkel, Ester; Papadakis, Nicolas; Gilboa, Guy: Nonlinear power method for computing eigenvectors of proximal operators and neural networks (2021)
  5. Chen, Yiting; Li, Jia; Yu, Qingyun: Large region inpainting by re-weighted regularized methods (2021)
  6. Chen, Yunmei; Liu, Hongcheng; Ye, Xiaojing; Zhang, Qingchao: Learnable descent algorithm for nonsmooth nonconvex image reconstruction (2021)
  7. Cohen, Regev; Elad, Michael; Milanfar, Peyman: Regularization by denoising via fixed-point projection (RED-PRO) (2021)
  8. Davy, Axel; Ehret, Thibaud; Morel, Jean-Michel; Arias, Pablo; Facciolo, Gabriele: Video denoising by combining patch search and CNNs (2021)
  9. Guo, Zhenfei; Bai, Ruixiang; Lei, Zhenkun; Jiang, Hao; Liu, Da; Zou, Jianchao; Yan, Cheng: CPINet: parameter identification of path-dependent constitutive model with automatic denoising based on CNN-LSTM (2021)
  10. Hertrich, Johannes; Neumayer, Sebastian; Steidl, Gabriele: Convolutional proximal neural networks and plug-and-play algorithms (2021)
  11. Jin, Qiyu; Grama, Ion; Liu, Quansheng: Poisson shot noise removal by an oracular non-local algorithm (2021)
  12. Mukhoty, Bhaskar; Dutta, Subhajit; Kar, Purushottam: Robust non-parametric regression via incoherent subspace projections (2021)
  13. Pesquet, Jean-Christophe; Repetti, Audrey; Terris, Matthieu; Wiaux, Yves: Learning maximally monotone operators for image recovery (2021)
  14. Pinetz, Thomas; Kobler, Erich; Pock, Thomas; Effland, Alexander: Shared prior learning of energy-based models for image reconstruction (2021)
  15. Tian, Wenyi; Yuan, Xiaoming; Yue, Hangrui: An ADMM-Newton-CNN numerical approach to a TV model for identifying discontinuous diffusion coefficients in elliptic equations: convex case with gradient observations (2021)
  16. Tirer, Tom; Giryes, Raja: On the convergence rate of projected gradient descent for a back-projection based objective (2021)
  17. Zhang, Ying; Ren, Xuhua; Clifford, Bryan Alexander; Wang, Qian; Zhang, Xiaoqun: Image fusion network for dual-modal restoration (2021)
  18. Zou, Qing; Jacob, Mathews: Recovery of surfaces and functions in high dimensions: sampling theory and links to neural networks (2021)
  19. Afraites, L.; Hadri, A.; Laghrib, A.: A denoising model adapted for impulse and Gaussian noises using a constrained-PDE (2020)
  20. Bertocchi, Carla; Chouzenoux, Emilie; Corbineau, Marie-Caroline; Pesquet, Jean-Christophe; Prato, Marco: Deep unfolding of a proximal interior point method for image restoration (2020)

1 2 3 next