{
  "id": "1711.02488",
  "version": "v1",
  "published": "2017-11-07T14:32:25.000Z",
  "updated": "2017-11-07T14:32:25.000Z",
  "title": "MSR-net:Low-light Image Enhancement Using Deep Convolutional Network",
  "authors": [
    "Liang Shen",
    "Zihan Yue",
    "Fan Feng",
    "Quan Chen",
    "Shihao Liu",
    "Jie Ma"
  ],
  "comment": "9pages",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Images captured in low-light conditions usually suffer from very low contrast, which increases the difficulty of subsequent computer vision tasks in a great extent. In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed. Firstly, we show that multi-scale Retinex is equivalent to a feedforward convolutional neural network with different Gaussian convolution kernels. Motivated by this fact, we consider a Convolutional Neural Network(MSR-net) that directly learns an end-to-end mapping between dark and bright images. Different fundamentally from existing approaches, low-light image enhancement in this paper is regarded as a machine learning problem. In this model, most of the parameters are optimized by back-propagation, while the parameters of traditional models depend on the artificial setting. Experiments on a number of challenging images reveal the advantages of our method in comparison with other state-of-the-art methods from the qualitative and quantitative perspective.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-11-07T14:32:25.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep convolutional network",
      "subsequent computer vision tasks",
      "low-light image enhancement model",
      "gaussian convolution kernels",
      "low-light conditions usually suffer"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 9,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}