# GSTran: Joint Geometric and Semantic Coherence for Point Cloud Segmentation

arXiv: https://arxiv.org/abs/2408.11558 · HTML: https://mlsanity.com/paper/2408.11558/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 21 Aug 2024.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)
- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://mlsanity.com/paper/2212.01558/) (2022)
- [Surface Representation for Point Clouds](https://mlsanity.com/paper/2205.05740/) (2022)
- [Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion](https://mlsanity.com/paper/2103.07074/) (2021)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [Self-positioning Point-based Transformer for Point Cloud Understanding](https://mlsanity.com/paper/2303.16450/) (2023)
- [Attention-based Point Cloud Edge Sampling](https://mlsanity.com/paper/2302.14673/) (2023)
- [Point Attention Network for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1909.12663/) (2019)
- [3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification](https://mlsanity.com/paper/2203.00828/) (2022)
- [Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding](https://mlsanity.com/paper/2312.02244/) (2023)
- [Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks](https://mlsanity.com/paper/2103.15226/) (2021)
- [Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation](https://mlsanity.com/paper/2111.07248/) (2021)
- [GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation](https://mlsanity.com/paper/2305.15213/) (2023)
- [Multi-scale Network with Attentional Multi-resolution Fusion for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2206.13628/) (2022)

## Built on by (most cited first, 1 of 1)

- [PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modeling](https://mlsanity.com/paper/2507.04801/) (2025)

## Abstract (arXiv)

Learning meaningful local and global information remains a challenge in point cloud segmentation tasks. When utilizing local information, prior studies indiscriminately aggregates neighbor information from different classes to update query points, potentially compromising the distinctive feature of query points. In parallel, inaccurate modeling of long-distance contextual dependencies when utilizing global information can also impact model performance. To address these issues, we propose GSTran, a novel transformer network tailored for the segmentation task. The proposed network mainly consists of two principal components: a local geometric transformer and a global semantic transformer. In the local geometric transformer module, we explicitly calculate the geometric disparity within the local region. This enables amplifying the affinity with geometrically similar neighbor points while suppressing the association with other neighbors. In the global semantic transformer module, we design a multi-head voting strategy. This strategy evaluates semantic similarity across the entire spatial range, facilitating the precise capture of contextual dependencies. Experiments on ShapeNetPart and S3DIS benchmarks demonstrate the effectiveness of the proposed method, showing its superiority over other algorithms. The code is available at https://github.com/LAB123-tech/GSTran.