{
  "id": "2004.05821",
  "version": "v1",
  "published": "2020-04-13T08:32:03.000Z",
  "updated": "2020-04-13T08:32:03.000Z",
  "title": "Monocular Depth Estimation with Self-supervised Instance Adaptation",
  "authors": [
    "Robert McCraith",
    "Lukas Neumann",
    "Andrew Zisserman",
    "Andrea Vedaldi"
  ],
  "comment": "IROS submission, 7 pages",
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics applications,multiple views of a scene may or may not be available, depend-ing on the actions of the robot, switching between monocularand multi-view reconstruction. To address this mixed setting,we proposed a new approach that extends any off-the-shelfself-supervised monocular depth reconstruction system to usemore than one image at test time. Our method builds on astandard prior learned to perform monocular reconstruction,but uses self-supervision at test time to further improve thereconstruction accuracy when multiple images are available.When used to update the correct components of the model, thisapproach is highly-effective. On the standard KITTI bench-mark, our self-supervised method consistently outperformsall the previous methods with an average 25% reduction inabsolute error for the three common setups (monocular, stereoand monocular+stereo), and comes very close in accuracy whencompared to the fully-supervised state-of-the-art methods.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-04-13T08:32:03.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "monocular depth estimation",
      "self-supervised instance adaptation",
      "test time",
      "learn accurate monoculardepth reconstruction",
      "off-the-shelfself-supervised monocular depth reconstruction system"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 7,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}