FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 206 - 215
• Main Authors: Yang, Yaoqing, Feng, Chen, Shen, Yiru, Tian, Dong
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Decoding; Image reconstruction; Neural networks; Surface reconstruction; Three-dimensional displays; Two dimensional displays

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 challenge...