# A boundary-aware point clustering approach in Euclidean and embedding spaces for roof plane segmentation

arXiv: https://arxiv.org/abs/2309.03722 · HTML: https://mlsanity.com/paper/2309.03722/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 69 references that are in the map.
- First posted on arXiv 7 Sep 2023.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://mlsanity.com/paper/1812.04072/) (2018)
- [Associatively Segmenting Instances and Semantics in Point Clouds](https://mlsanity.com/paper/1902.09852/) (2019)
- [PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1804.06278/) (2018)
- [JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields](https://mlsanity.com/paper/1904.00699/) (2019)
- [Embedding Projector: Interactive Visualization and Interpretation of Embeddings](https://mlsanity.com/paper/1611.05469/) (2016)
- [HPNet: Deep Primitive Segmentation Using Hybrid Representations](https://mlsanity.com/paper/2105.10620/) (2021)
- [PlaneTR: Structure-Guided Transformers for 3D Plane Recovery](https://mlsanity.com/paper/2107.13108/) (2021)
- [PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2203.12082/) (2022)
- [Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization](https://mlsanity.com/paper/2207.11209/) (2022)
- [Building3D: An Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Clouds](https://mlsanity.com/paper/2307.11914/) (2023)
- [Dynamic Convolution for 3D Point Cloud Instance Segmentation](https://mlsanity.com/paper/2107.08392/) (2021)

## Built on by (most cited first, 3 of 3)

- [SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Clouds](https://mlsanity.com/paper/2505.24475/) (2025)
- [PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model](https://mlsanity.com/paper/2410.16545/) (2024)
- [RoofSeg: An edge-aware transformer-based network for end-to-end roof plane segmentation](https://mlsanity.com/paper/2508.19003/) (2025)

## Abstract (arXiv)

Roof plane segmentation from airborne LiDAR point clouds is an important technology for 3D building model reconstruction. One of the key issues of plane segmentation is how to design powerful features that can exactly distinguish adjacent planar patches. The quality of point feature directly determines the accuracy of roof plane segmentation. Most of existing approaches use handcrafted features to extract roof planes. However, the abilities of these features are relatively low, especially in boundary area. To solve this problem, we propose a boundary-aware point clustering approach in Euclidean and embedding spaces constructed by a multi-task deep network for roof plane segmentation. We design a three-branch network to predict semantic labels, point offsets and extract deep embedding features. In the first branch, we classify the input data as non-roof, boundary and plane points. In the second branch, we predict point offsets for shifting each point toward its respective instance center. In the third branch, we constrain that points of the same plane instance should have the similar embeddings. We aim to ensure that points of the same plane instance are close as much as possible in both Euclidean and embedding spaces. However, although deep network has strong feature representative ability, it is still hard to accurately distinguish points near plane instance boundary. Therefore, we first group plane points into many clusters in the two spaces, and then we assign the rest boundary points to their closest clusters to generate final complete roof planes. In this way, we can effectively reduce the influence of unreliable boundary points. In addition, we prepare a synthetic dataset and two real datasets to train and evaluate our approach. The experiments results show that the proposed approach significantly outperforms the existing state-of-the-art approaches.