Corpus ID: 166228003

GRDN: Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling

@inproceedings{Kim2019GRDNGR,
  title={GRDN: Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling},
  author={Dong-Wook Kim and Jae Ryun Chung and Seung-Won Jung},
  booktitle={CVPR Workshops},
  year={2019}
}
  • Dong-Wook Kim, Jae Ryun Chung, Seung-Won Jung
  • Published in CVPR Workshops 2019
  • Engineering, Computer Science
  • Recent research on image denoising has progressed with the development of deep learning architectures, especially convolutional neural networks. [...] Key Method The core part of RDN is defined as grouped residual dense block (GRDB) and used as a building module of GRDN. We experimentally show that the image denoising performance can be significantly improved by cascading GRDBs.Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-9 OF 9 CITATIONS

    Low Bit-rate Image Compression based on Post-processing with Grouped Residual Dense Network

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND

    NTIRE 2019 Challenge on Real Image Denoising: Methods and Results

    VIEW 14 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    AIM 2019 Challenge on Image Demoireing: Dataset and Study

    AIM 2019 Challenge on Image Demoireing: Methods and Results

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    Image Processing Using Multi-Code GAN Prior

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES

    CBAM: Convolutional Block Attention Module

    VIEW 14 EXCERPTS
    HIGHLY INFLUENTIAL

    A High-Quality Denoising Dataset for Smartphone Cameras

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Residual Dense Network for Image Super-Resolution

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Image Super-Resolution Using Very Deep Residual Channel Attention Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Residual Dense Network for Image Restoration

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Benchmarking Denoising Algorithms with Real Photographs

    • Tobias Plotz, Stefan Roth
    • Computer Science
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    DeepISP: Toward Learning an End-to-End Image Processing Pipeline