{
  "id": "1903.10297",
  "version": "v1",
  "published": "2019-03-25T13:14:23.000Z",
  "updated": "2019-03-25T13:14:23.000Z",
  "title": "CoSegNet: Deep Co-Segmentation of 3D Shapes with Group Consistency Loss",
  "authors": [
    "Chenyang Zhu",
    "Kai Xu",
    "Siddhartha Chaudhuri",
    "Li Yi",
    "Leonidas Guibas",
    "Hao Zhang"
  ],
  "categories": [
    "cs.CV",
    "cs.GR"
  ],
  "abstract": "We introduce CoSegNet, a deep neural network architecture for co-segmentation of a set of 3D shapes represented as point clouds. CoSegNet takes as input a set of unsegmented shapes, proposes per-shape parts, and then jointly optimizes the part labelings across the set subjected to a novel group consistency loss expressed via matrix rank estimates. The proposals are refined in each iteration by an auxiliary network that acts as a weak regularizing prior, pre-trained to denoise noisy, unlabeled parts from a large collection of segmented 3D shapes, where the part compositions within the same object category can be highly inconsistent. The output is a consistent part labeling for the input set, with each shape segmented into up to K (a user-specified hyperparameter) parts. The overall pipeline is thus weakly supervised, producing consistent segmentations tailored to the test set, without consistent ground-truth segmentations. We show qualitative and quantitative results from CoSegNet and evaluate it via ablation studies and comparisons to state-of-the-art co-segmentation methods.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-03-25T13:14:23.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "3d shapes",
      "deep co-segmentation",
      "deep neural network architecture",
      "novel group consistency loss",
      "matrix rank estimates"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}