# Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations

arXiv: https://arxiv.org/abs/1911.05277 · HTML: https://mlsanity.com/paper/1911.05277/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2019.

## Built on by (most cited first, 10 of 10)

- [Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds](https://mlsanity.com/paper/2101.02381/) (2021)
- [Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning](https://mlsanity.com/paper/2105.10203/) (2021)
- [CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2307.10316/) (2023)
- [Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning](https://mlsanity.com/paper/2211.06841/) (2022)
- [DLA-Net: Learning Dual Local Attention Features for Semantic Segmentation of Large-Scale Building Facade Point Clouds](https://mlsanity.com/paper/2106.00376/) (2021)
- [D-Net: Learning for Distinctive Point Clouds by Self-Attentive Point Searching and Learnable Feature Fusion](https://mlsanity.com/paper/2305.05842/) (2023)
- [Similarity-Aware Fusion Network for 3D Semantic Segmentation](https://mlsanity.com/paper/2107.01579/) (2021)
- [Hierarchical Point Cloud Encoding and Decoding with Lightweight Self-Attention based Model](https://mlsanity.com/paper/2202.06407/) (2022)
- [Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysis](https://mlsanity.com/paper/2211.10888/) (2022)
- [Global Attention-Guided Dual-Domain Point Cloud Feature Learning for Classification and Segmentation](https://mlsanity.com/paper/2407.08994/) (2024)

## Abstract (arXiv)

In this paper, we propose one novel model for point cloud semantic segmentation, which exploits both the local and global structures within the point cloud based on the contextual point representations. Specifically, we enrich each point representation by performing one novel gated fusion on the point itself and its contextual points. Afterwards, based on the enriched representation, we propose one novel graph pointnet module, relying on the graph attention block to dynamically compose and update each point representation within the local point cloud structure. Finally, we resort to the spatial-wise and channel-wise attention strategies to exploit the point cloud global structure and thereby yield the resulting semantic label for each point. Extensive results on the public point cloud databases, namely the S3DIS and ScanNet datasets, demonstrate the effectiveness of our proposed model, outperforming the state-of-the-art approaches. Our code for this paper is available at https://github.com/fly519/ELGS.