# LSANet: Feature Learning on Point Sets by Local Spatial Aware Layer

arXiv: https://arxiv.org/abs/1905.05442 · HTML: https://mlsanity.com/paper/1905.05442/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2019.

## Built on by (most cited first, 5 of 5)

- [Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook](https://mlsanity.com/paper/2311.02608/) (2023)
- [Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities](https://mlsanity.com/paper/2212.02287/) (2022)
- [Differentiable Convolution Search for Point Cloud Processing](https://mlsanity.com/paper/2108.12856/) (2021)
- [Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey](https://mlsanity.com/paper/2402.12923/) (2024)
- [Deep Algebraic Fitting for Multiple Circle Primitives Extraction from Raw Point Clouds](https://mlsanity.com/paper/2204.00920/) (2022)

## Abstract (arXiv)

Directly learning features from the point cloud has become an active research direction in 3D understanding. Existing learning-based methods usually construct local regions from the point cloud and extract the corresponding features. However, most of these processes do not adequately take the spatial distribution of the point cloud into account, limiting the ability to perceive fine-grained patterns. We design a novel Local Spatial Aware (LSA) layer, which can learn to generate Spatial Distribution Weights (SDWs) hierarchically based on the spatial relationship in local region for spatial independent operations, to establish the relationship between these operations and spatial distribution, thus capturing the local geometric structure sensitively.We further propose the LSANet, which is based on LSA layer, aggregating the spatial information with associated features in each layer of the network better in network design.The experiments show that our LSANet can achieve on par or better performance than the state-of-the-art methods when evaluating on the challenging benchmark datasets. For example, our LSANet can achieve 93.2% accuracy on ModelNet40 dataset using only 1024 points, significantly higher than other methods under the same conditions. The source code is available at https://github.com/LinZhuoChen/LSANet.