{
  "id": "2103.15536",
  "version": "v1",
  "published": "2021-03-29T12:09:42.000Z",
  "updated": "2021-03-29T12:09:42.000Z",
  "title": "Cloud2Curve: Generation and Vectorization of Parametric Sketches",
  "authors": [
    "Ayan Das",
    "Yongxin Yang",
    "Timothy Hospedales",
    "Tao Xiang",
    "Yi-Zhe Song"
  ],
  "comment": "Accepted at CVPR 2021 (Poster)",
  "categories": [
    "cs.CV",
    "cs.AI"
  ],
  "abstract": "Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketches as a sequence of low-dimensional parametric curves. To this end, we propose an inverse graphics framework capable of approximating a raster or waypoint based stroke encoded as a point-cloud with a variable-degree B\\'ezier curve. Building on this module, we present Cloud2Curve, a generative model for scalable high-resolution vector sketches that can be trained end-to-end using point-cloud data alone. As a consequence, our model is also capable of deterministic vectorization which can map novel raster or waypoint based sketches to their corresponding high-resolution scalable B\\'ezier equivalent. We evaluate the generation and vectorization capabilities of our model on Quick, Draw! and K-MNIST datasets.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-03-29T12:09:42.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "parametric sketches",
      "vectorization",
      "generation",
      "cloud2curve",
      "scalable high-resolution vector sketches"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}