{
  "id": "1604.02245",
  "version": "v1",
  "published": "2016-04-08T07:10:47.000Z",
  "updated": "2016-04-08T07:10:47.000Z",
  "title": "Infrared Colorization Using Deep Convolutional Neural Networks",
  "authors": [
    "Matthias Limmer",
    "Hendrik P. A. Lensch"
  ],
  "comment": "6 pages, 8 figures, submitted to ICPR2016",
  "categories": [
    "cs.CV",
    "cs.GR"
  ],
  "abstract": "This paper proposes a method for transferring the RGB color spectrum to near-infrared (NIR) images using deep multi-scale convolutional neural networks. A direct and integrated transfer between NIR and RGB pixels is trained. The trained model does not require any user guidance or a reference image database in the recall phase to produce images with a natural appearance. To preserve the rich details of the NIR image, its high frequency features are transferred to the estimated RGB image. The presented approach is trained and evaluated on a real-world dataset containing a large amount of road scene images in summer. The dataset was captured by a multi-CCD NIR/RGB camera, which ensures a perfect pixel to pixel registration.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-04-08T07:10:47.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "82C32",
      "68T45",
      "H.5.1",
      "I.4.8",
      "I.5.1"
    ],
    "keywords": [
      "deep convolutional neural networks",
      "infrared colorization",
      "deep multi-scale convolutional neural networks",
      "rgb color spectrum",
      "reference image database"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 6,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2016arXiv160402245L"
    }
  }
}