Color constancy using CNNs

@article{Bianco2015ColorCU,
  title={Color constancy using CNNs},
  author={S. Bianco and C. Cusano and R. Schettini},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2015},
  pages={81-89}
}
  • S. Bianco, C. Cusano, R. Schettini
  • Published 2015
  • Computer Science
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most previous methods. The network consists of one convolutional layer with max pooling, one fully connected layer and three output nodes. Within the network structure, feature learning and regression are integrated into one optimization process, which leads to a… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    FC^4: Fully Convolutional Color Constancy with Confidence-Weighted Pooling
    • 89
    • Highly Influenced
    • PDF
    Approaching the computational color constancy as a classification problem through deep learning
    • 54
    • PDF
    Mixed pooling neural networks for color constancy
    • 18
    • Highly Influenced
    • PDF
    Single and Multiple Illuminant Estimation Using Convolutional Neural Networks
    • 63
    • PDF
    Improving CNN-Based Texture Classification by Color Balancing
    • 13
    • PDF
    Quasi-Unsupervised Color Constancy
    • 14
    • PDF
    Color Constancy by Deep Learning
    • 30
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES
    Going deeper with convolutions
    • 20,016
    • PDF
    Color constancy using faces
    • 70
    • PDF
    ImageNet classification with deep convolutional neural networks
    • 52,445
    • Highly Influential
    • PDF
    Exemplar-Based Color Constancy and Multiple Illumination
    • 106
    • PDF
    Caffe: Convolutional Architecture for Fast Feature Embedding
    • 12,125
    • Highly Influential
    • PDF
    Computational Color Constancy: Survey and Experiments
    • 437
    • PDF
    Automatic color constancy algorithm selection and combination
    • 97
    • PDF
    Learning Convolutional Feature Hierarchies for Visual Recognition
    • 518
    • PDF
    Color Constancy with Spatio-Spectral Statistics
    • 142
    • PDF
    White Point Estimation for Uncalibrated Images
    • 62
    • PDF