Local-Area-Learning Network: Meaningful Local Areas for Efficient Point Cloud Analysis

by   Qendrim Bytyqi, et al.

Research in point cloud analysis with deep neural networks has made rapid progress in recent years. The pioneering work PointNet offered a direct analysis of point clouds. However, due to its architecture PointNet is not able to capture local structures. To overcome this drawback, the same authors have developed PointNet++ by applying PointNet to local areas. The local areas are defined by center points and their neighbors. In PointNet++ and its further developments the center points are determined with a Farthest Point Sampling (FPS) algorithm. This has the disadvantage that the center points in general do not have meaningful local areas. In this paper, we introduce the neural Local-Area-Learning Network (LocAL-Net) which places emphasis on the selection and characterization of the local areas. Our approach learns critical points that we use as center points. In order to strengthen the recognition of local structures, the points are given additional metric properties depending on the local areas. Finally, we derive and combine two global feature vectors, one from the whole point cloud and one from all local areas. Experiments on the datasets ModelNet10/40 and ShapeNet show that LocAL-Net is competitive for part segmentation. For classification LocAL-Net outperforms the state-of-the-arts.



There are no comments yet.


page 3


Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud

This paper investigates the indistinguishable points (difficult to predi...

APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification

Point-cloud-based 3D classification task involves aggregating features f...

SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processing

Deep neural networks have established themselves as the state-of-the-art...

Adaptive Hierarchical Down-Sampling for Point Cloud Classification

While several convolution-like operators have recently been proposed for...

Spatial Transformer for 3D Points

Point cloud is an efficient representation of 3D visual data, and enable...

Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentation

We present an innovative two-headed attention layer that combines geomet...

Self-Sampling for Neural Point Cloud Consolidation

In this paper, we introduce a deep learning technique for consolidating ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.