Multiresolution Tree Networks for 3D Point Cloud Processing

Abstract

We present multiresolution tree-structured networks to process point clouds for 3D shape understanding and generation tasks. Our network represents a 3D shape as a set of locality-preserving 1D ordered list of points at multiple resolutions. This allows efficient feed-forward processing through 1D convolutions, coarse-to-fine analysis through a multi-grid architecture, and it leads to faster convergence and small memory footprint during training. The proposed tree-structured encoders can be used to classify shapes and outperform existing point-based architectures on shape classification benchmarks, while tree-structured decoders can be used for generating point clouds directly and they outperform existing approaches for image-to-shape inference tasks learned using the ShapeNet dataset. Our model also allows unsupervised learning of point-cloud based shapes by using a variational autoencoder, leading to higher-quality generated shapes.

Accepted to ECCV 2018. 23 pages, including supplemental material

Cited by in corpus (11)

• Patch-based Progressive 3D Point Set Upsampling
• Spatial Transformer for 3D Point Clouds
• PIG-Net: Inception based Deep Learning Architecture for 3D Point Cloud Segmentation
• PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention
• Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
• Learning Mesh Representations via Binary Space Partitioning Tree Networks
• ChartPointFlow for Topology-Aware 3D Point Cloud Generation
• Geometry Sharing Network for 3D Point Cloud Classification and Segmentation
• Energy-Based Processes for Exchangeable Data
• POIRot: A rotation invariant omni-directional pointnet
• MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis