{
  "id": "2108.05054",
  "version": "v1",
  "published": "2021-08-11T06:37:01.000Z",
  "updated": "2021-08-11T06:37:01.000Z",
  "title": "Rethinking Coarse-to-Fine Approach in Single Image Deblurring",
  "authors": [
    "Sung-Jin Cho",
    "Seo-Won Ji",
    "Jun-Pyo Hong",
    "Seung-Won Jung",
    "Sung-Jea Ko"
  ],
  "comment": "Accepted by IEEE International Conference on Computer Vision (ICCV) 2021",
  "categories": [
    "cs.CV",
    "cs.AI"
  ],
  "abstract": "Coarse-to-fine strategies have been extensively used for the architecture design of single image deblurring networks. Conventional methods typically stack sub-networks with multi-scale input images and gradually improve sharpness of images from the bottom sub-network to the top sub-network, yielding inevitably high computational costs. Toward a fast and accurate deblurring network design, we revisit the coarse-to-fine strategy and present a multi-input multi-output U-net (MIMO-UNet). The MIMO-UNet has three distinct features. First, the single encoder of the MIMO-UNet takes multi-scale input images to ease the difficulty of training. Second, the single decoder of the MIMO-UNet outputs multiple deblurred images with different scales to mimic multi-cascaded U-nets using a single U-shaped network. Last, asymmetric feature fusion is introduced to merge multi-scale features in an efficient manner. Extensive experiments on the GoPro and RealBlur datasets demonstrate that the proposed network outperforms the state-of-the-art methods in terms of both accuracy and computational complexity. Source code is available for research purposes at https://github.com/chosj95/MIMO-UNet.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-08-11T06:37:01.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "single image deblurring",
      "rethinking coarse-to-fine approach",
      "outputs multiple deblurred images",
      "methods typically stack sub-networks",
      "inevitably high computational costs"
    ],
    "tags": [
      "conference paper"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}