FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation
Abstract
Recent deep networks that directly handle points in a point set, e.g., PointNet, have been state-of-the-art for supervised learning tasks on point clouds such as classification and segmentation. In this work, a novel end-to-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 decoder deforms a canonical 2D grid onto the underlying 3D object surface of a point cloud, achieving low reconstruction errors even for objects with delicate structures. 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. Our code is available at http://www.merl.com/research/license#FoldingNet
Cite
@article{arxiv.1712.07262,
title = {FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation},
author = {Yaoqing Yang and Chen Feng and Yiru Shen and Dong Tian},
journal= {arXiv preprint arXiv:1712.07262},
year = {2018}
}
Comments
Accepted as a spotlight paper in CVPR'18