Learning Raw Image Denoising With Bayer Pattern Unification and Bayer Preserving Augmentation

@article{Liu2019LearningRI,
  title={Learning Raw Image Denoising With Bayer Pattern Unification and Bayer Preserving Augmentation},
  author={Jiaming Liu and C. F. Jeff Wu and Yuzhi Wang and Qin Xu and Yuqian Zhou and Haibin Huang and Chuan Wang and Shaofan Cai and Yifan Ding and Haoqiang Fan and Jue Wang},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2019},
  pages={2070-2077}
}
  • Jiaming Liu, C. F. Jeff Wu, +8 authors Jue Wang
  • Published 2019
  • Computer Science, Engineering
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • In this paper, we present new data pre-processing and augmentation techniques for DNN-based raw image denoising. Compared with traditional RGB image denoising, performing this task on direct camera sensor readings presents new challenges such as how to effectively handle various Bayer patterns from different data sources, and subsequently how to perform valid data augmentation with raw images. To address the first problem, we propose a Bayer pattern unification (BayerUnify) method to unify… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 12 CITATIONS

    CycleISP: Real Image Restoration via Improved Data Synthesis

    VIEW 2 EXCERPTS
    CITES METHODS

    Supervised Raw Video Denoising With a Benchmark Dataset on Dynamic Scenes

    VIEW 1 EXCERPT
    CITES BACKGROUND

    NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results

    VIEW 3 EXCERPTS
    CITES METHODS

    NTIRE 2019 Challenge on Real Image Denoising: Methods and Results

    VIEW 1 EXCERPT
    CITES METHODS

    Attention Mechanism Enhanced Kernel Prediction Networks for Denoising of Burst Images

    Image Restoration for Under-Display Camera

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latency

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Adaptive Regularization of Some Inverse Problems in Image Analysis

    Semi-Supervised Skin Detection by Network With Mutual Guidance

    • Yi He, Jiayuan Shi, +5 authors Jue Wang
    • Computer Science
    • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
    • 2019
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Real Image Denoising Based on Multi-Scale Residual Dense Block and Cascaded U-Net with Block-Connection

    VIEW 3 EXCERPTS
    HIGHLY INFLUENCED

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 36 REFERENCES

    Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

    VIEW 1 EXCERPT

    FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising

    VIEW 1 EXCERPT

    Deep Image Prior

    VIEW 2 EXCERPTS

    Non-local sparse models for image restoration

    VIEW 1 EXCERPT

    Learning to See in the Dark

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Joint demosaicing and denoising

    VIEW 1 EXCERPT

    RENOIR - A dataset for real low-light image noise reduction

    VIEW 2 EXCERPTS