TR2017-193

FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds


    •  Yang, Y., Feng, C., Shen, Y., Tian, D., "FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds," Tech. Rep. TR2017-193, arXiv, December 2017.
      BibTeX Download PDF
      • @techreport{MERL_TR2017-193,
      • author = {Yang, Y. and Feng, C. and Shen, Y. and Tian, D.},
      • title = {FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR2017-193},
      • month = dec,
      • year = 2017,
      • url = {http://www.merl.com/publications/TR2017-193/}
      • }
  • Research Areas:

    Computer Vision, Machine Learning

  • Download Freely Available:

    FoldingNet — FoldingNet


Recent deep networks that directly handle points in a point set, e.g., PointNet, have been state-of-the-art for supervised semantic learning tasks on point clouds such as classification and segmentation. In this work, a novel endto-end deep auto-encoder is proposed to address unsupervised learning challenges on point clouds. On the encoder side, a graph-based enhancement is enforced to promote local structures on top of PointNet. Then, a novel folding based approach is proposed in the decoder, which folds a 2D grid onto the underlying 3D object surface of a point cloud. The proposed decoder only uses about 7% parameters of a decoder with fully-connected neural networks, yet leads to a more discriminative representation that achieves higher linear SVM classification accuracy than the benchmark. In addition, the proposed decoder structure is shown, in theory, to be a generic architecture that is able to reconstruct an arbitrary point cloud from a 2D grid. Finally, this folding-based decoder is interpretable since the reconstruction could be viewed as a fine granular warping from the 2D grid to the point cloud surface.