Multiresolution Tree Networks for 3D Point Cloud Processing
This work addresses efficient and accurate 3D shape analysis and generation for computer vision applications, representing an incremental improvement over existing point-based architectures.
The paper tackles 3D point cloud processing by introducing multiresolution tree-structured networks for shape understanding and generation, achieving faster convergence, small memory footprint, and outperforming existing methods on classification and image-to-shape inference tasks using the ShapeNet dataset.
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.