{
  "id": "2006.07982",
  "version": "v1",
  "published": "2020-06-14T19:03:35.000Z",
  "updated": "2020-06-14T19:03:35.000Z",
  "title": "ShapeFlow: Learnable Deformations Among 3D Shapes",
  "authors": [
    "Chiyu \"Max\" Jiang",
    "Jingwei Huang",
    "Andrea Tagliasacchi",
    "Leonidas Guibas"
  ],
  "categories": [
    "cs.CV",
    "cs.GR"
  ],
  "abstract": "We present ShapeFlow, a flow-based model for learning a deformation space for entire classes of 3D shapes with large intra-class variations. ShapeFlow allows learning a multi-template deformation space that is agnostic to shape topology, yet preserves fine geometric details. Different from a generative space where a latent vector is directly decoded into a shape, a deformation space decodes a vector into a continuous flow that can advect a source shape towards a target. Such a space naturally allows the disentanglement of geometric style (coming from the source) and structural pose (conforming to the target). We parametrize the deformation between geometries as a learned continuous flow field via a neural network and show that such deformations can be guaranteed to have desirable properties, such as be bijectivity, freedom from self-intersections, or volume preservation. We illustrate the effectiveness of this learned deformation space for various downstream applications, including shape generation via deformation, geometric style transfer, unsupervised learning of a consistent parameterization for entire classes of shapes, and shape interpolation.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-06-14T19:03:35.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "3d shapes",
      "learnable deformations",
      "entire classes",
      "multi-template deformation space",
      "large intra-class variations"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}