{
  "id": "2205.13682",
  "version": "v1",
  "published": "2022-05-27T00:01:40.000Z",
  "updated": "2022-05-27T00:01:40.000Z",
  "title": "ANISE: Assembly-based Neural Implicit Surface rEconstruction",
  "authors": [
    "Dmitry Petrov",
    "Matheus Gadelha",
    "Radomir Mech",
    "Evangelos Kalogerakis"
  ],
  "comment": "8 pages, 5 figures, 4 tables",
  "categories": [
    "cs.CV",
    "cs.GR"
  ],
  "abstract": "We present ANISE, a method that reconstructs a 3D shape from partial observations (images or sparse point clouds) using a part-aware neural implicit shape representation. It is formulated as an assembly of neural implicit functions, each representing a different shape part. In contrast to previous approaches, the prediction of this representation proceeds in a coarse-to-fine manner. Our network first predicts part transformations which are associated with part neural implicit functions conditioned on those transformations. The part implicit functions can then be combined into a single, coherent shape, enabling part-aware shape reconstructions from images and point clouds. Those reconstructions can be obtained in two ways: (i) by directly decoding combining the refined part implicit functions; or (ii) by using part latents to query similar parts in a part database and assembling them in a single shape. We demonstrate that, when performing reconstruction by decoding part representations into implicit functions, our method achieves state-of-the-art part-aware reconstruction results from both images and sparse point clouds. When reconstructing shapes by assembling parts queried from a dataset, our approach significantly outperforms traditional shape retrieval methods even when significantly restricting the size of the shape database. We present our results in well-known sparse point cloud reconstruction and single-view reconstruction benchmarks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-05-27T00:01:40.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "assembly-based neural implicit surface reconstruction",
      "sparse point cloud",
      "neural implicit functions",
      "outperforms traditional shape",
      "traditional shape retrieval"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}