Research License — FoldingNet++

FoldingNet++ for unsupervised learning of 3D point clouds with data-adaptive graph prior.

This software is the pytorch implementation of FoldingNet++, which is a novel end-to-end graph-based deep autoencoder to achieve compact representations of unorganized 3D point clouds in an unsupervised manner.

The encoder of the proposed networks adopts similar architectures as in PointNet, which is a well-acknowledged method for supervised learning of 3D point clouds, such as recognition and segmentation. The decoder of the proposed networks involves three novel modules: folding module, graph-topology-inference module, and graph-filtering module. The folding module folds a canonical 2D lattice to the underlying surface of a 3D point cloud, achieving coarse reconstruction; the graph-topology-inference module learns a graph topology to represent pairwise relationships between 3D points, pushing the latent code to preserve both coordinates and pairwise relationships of points in 3D point clouds; the graph-filtering module designs graph filters based on the learnt graph topology and refines the coarse reconstruction to obtain the final reconstruction. The experimental results associated with this software show that the proposed networks outperform the state-of-the-art methods in various tasks, including recontruction and transfer classification.

  •  Chen, S., Duan, C., Yang, Y., Feng, C., Li, D., Tian, D., "Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering", IEEE Transactions on Image Processing, DOI: 10.1109/TIP.2019.2957935, pp. 3183-3198, January 2020.
    BibTeX TR2020-004 PDF Software
    • @article{Chen2020jan,
    • author = {Chen, Siheng and Duan, Chaojing and Yang, Yaoqing and Feng, Chen and Li, Duanshun and Tian, Dong},
    • title = {Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering},
    • journal = {IEEE Transactions on Image Processing},
    • year = 2020,
    • pages = {3183--3198},
    • month = jan,
    • doi = {10.1109/TIP.2019.2957935},
    • url = {https://www.merl.com/publications/TR2020-004}
    • }

To download the software, please enter some information about yourself, then review and agree to MERL's research-only licensing terms.

    Software:
    Name:
    Affiliation:
    Street Address:
    City, State, Country, Postal Code:
    E-Mail:
    Confirm E-Mail: