Point Cloud Completion by Learning Shape Priors

In view of the difficulty in reconstructing object details in point cloud completion, we propose a shape prior learning method for object completion. The shape priors include geometric information in both complete and the partial point clouds. We design a feature alignment strategy to learn the shape prior from complete points, and a coarse to fine strategy to incorporate partial prior in the fine stage. To learn the complete objects prior, we first train a point cloud auto-encoder to extract the latent embeddings from complete points. Then we learn a mapping to transfer the point features from partial points to that of the complete points by optimizing feature alignment losses. The feature alignment losses consist of a L2 distance and an adversarial loss obtained by Maximum Mean Discrepancy Generative Adversarial Network (MMD-GAN). The L2 distance optimizes the partial features towards the complete ones in the feature space, and MMD-GAN decreases the statistical distance of two point features in a Reproducing Kernel Hilbert Space. We achieve state-of-the-art performances on the point cloud completion task. Our code is available at https://github.com/xiaogangw/point-cloud-completion-shape-prior.

Authors

• Xiaogang Wang 0008
• Marcelo H. Ang
• Gim Hee Lee

Keywords

• Learning systems
• Three-dimensional displays
• Shape
• Task analysis
• Kernel
• Optimization
• Intelligent robots
• Point Cloud
• Shape Priors
• Point Cloud Completion
• Generative Adversarial Networks
• Feature Points
• Feature Alignment
• Partial Point
• Reproducing Kernel Hilbert Space
• Maximum Mean Discrepancy
• Statistical Distance
• Complete Object
• Latent Embedding
• Convolutional Neural Network
• Deep Neural Network
• Qualitative Results
• Small Data
• Multilayer Perceptron
• Object Shape
• Feature Matching
• 3D Point Cloud
• Dense Point Cloud
• Image Transformation
• Simultaneous Localization And Mapping
• Earth Mover’s Distance
• Small Training Data
• Reconstruction Loss
• Point Cloud Classification
• KITTI Dataset
• Sparse Point Cloud
• Chamfer Distance