# PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation

## TL;DR

PS^2-Net is a novel deep learning framework for 3D point cloud semantic segmentation that effectively captures local and global features while ensuring permutation invariance, leading to state-of-the-art results.

## Contribution

The paper introduces PS^2-Net, a permutation-invariant network that combines local EdgeConv and global NetVLAD modules for improved 3D scene segmentation.

## Key findings

- Achieves state-of-the-art performance on large-scale 3D indoor datasets.
- Guarantees permutation invariance through theoretical proof.
- Effectively integrates local and global features for semantic segmentation.

## Abstract

In this paper, we present the PS^2-Net -- a locally and globally aware deep learning framework for semantic segmentation on 3D scene-level point clouds. In order to deeply incorporate local structures and global context to support 3D scene segmentation, our network is built on four repeatedly stacked encoders, where each encoder has two basic components: EdgeConv that captures local structures and NetVLAD that models global context. Different from existing start-of-the-art methods for point-based scene semantic segmentation that either violate or do not achieve permutation invariance, our PS^2-Net is designed to be permutation invariant which is an essential property of any deep network used to process unordered point clouds. We further provide theoretical proof to guarantee the permutation invariance property of our network. We perform extensive experiments on two large-scale 3D indoor scene datasets and demonstrate that our PS2-Net is able to achieve state-of-the-art performances as compared to existing approaches.