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% 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 https://www.merl.com/research/license#FoldingNet
Keywords for this software
References in zbMATH (referenced in 3 articles )
Showing results 1 to 3 of 3.
- Nicolas Wagner, Ulrich Schwanecke: NeuralQAAD: An Efficient Differentiable Framework for High Resolution Point Cloud Compression (2020) arXiv
- Zhang, Wenxiao; Long, Chengjiang; Yan, Qingan; Chow, Alix L. H.; Xiao, Chunxia: Multi-stage point completion network with critical set supervision (2020)
- Rezaei, Masoumeh; Rezaeian, Mehdi; Derhami, Vali; Sohel, Ferdous; Bennamoun, Mohammed: Deep learning-based 3D local feature descriptor from mercator projections (2019)