{
  "id": "2206.07259",
  "version": "v1",
  "published": "2022-06-15T02:43:39.000Z",
  "updated": "2022-06-15T02:43:39.000Z",
  "title": "Self-Supervised Learning of Image Scale and Orientation",
  "authors": [
    "Jongmin Lee",
    "Yoonwoo Jeong",
    "Minsu Cho"
  ],
  "comment": "Presented in BMVC 2021, code is available on https://github.com/bluedream1121/self-sca-ori",
  "categories": [
    "cs.CV"
  ],
  "abstract": "We study the problem of learning to assign a characteristic pose, i.e., scale and orientation, for an image region of interest. Despite its apparent simplicity, the problem is non-trivial; it is hard to obtain a large-scale set of image regions with explicit pose annotations that a model directly learns from. To tackle the issue, we propose a self-supervised learning framework with a histogram alignment technique. It generates pairs of image patches by random rescaling/rotating and then train an estimator to predict their scale/orientation values so that their relative difference is consistent with the rescaling/rotating used. The estimator learns to predict a non-parametric histogram distribution of scale/orientation without any supervision. Experiments show that it significantly outperforms previous methods in scale/orientation estimation and also improves image matching and 6 DoF camera pose estimation by incorporating our patch poses into a matching process.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-06-15T02:43:39.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "image scale",
      "self-supervised learning",
      "image region",
      "dof camera pose estimation",
      "scale/orientation"
    ],
    "tags": [
      "github project"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}