Learning Deep CNN Denoiser Prior for Image Restoration

@article{Zhang2017LearningDC,
  title={Learning Deep CNN Denoiser Prior for Image Restoration},
  author={Kai Zhang and Wangmeng Zuo and Shuhang Gu and Lei Zhang},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={2808-2817}
}
Model-based optimization methods and discriminative learning methods have been the two dominant strategies for solving various inverse problems in low-level vision. Typically, those two kinds of methods have their respective merits and drawbacks, e.g., model-based optimization methods are flexible for handling different inverse problems but are usually time-consuming with sophisticated priors for the purpose of good performance, in the meanwhile, discriminative learning methods have fast… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 218 CITATIONS, ESTIMATED 99% COVERAGE

Denoising Prior Driven Deep Neural Network for Image Restoration

  • IEEE transactions on pattern analysis and machine intelligence
  • 2018
VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Unified Single-Image and Video Super-Resolution via Denoising Algorithms.

  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • 2018
VIEW 13 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Image Restoration using Autoencoding Priors

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Convolutional Neural Network and Guided Filtering for SAR Image Denoising

  • Remote Sensing
  • 2019
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Densely Residual Laplacian Super-Resolution

VIEW 10 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

Gradient Prior-Aided CNN Denoiser With Separable Convolution-Based Optimization of Feature Dimension

  • IEEE Transactions on Multimedia
  • 2019
VIEW 21 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Plug-and-Play Methods Provably Converge with Properly Trained Denoisers

  • ICML
  • 2019
VIEW 17 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning

  • IEEE Signal Processing Letters
  • 2019
VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 73 Highly Influenced Citations

  • Averaged 72 Citations per year from 2017 through 2019

References

Publications referenced by this paper.