swMATH ID: 32562
Software Authors: Yaoqing Yang, Chen Feng, Yiru Shen, Dong Tian
Description: FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation. 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
Homepage: https://arxiv.org/abs/1712.07262
Dependencies: None
Keywords: Computer Vision and Pattern Recognition (cs.CV)
Related Software: PointNet; D-Faust; COMA; Adam; PyTorch; AtlasNet; VoxelNet; DeepSDF; NeuralQAAD; Wasserstein GAN; GRAF; KPConv; PointCNN; MeshCNN; t-SNE; EMD; SPLATNet; ScanComplete; PCL; BundleFusion
Cited in: 3 Publications

Citations by Year