# Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

arXiv: https://arxiv.org/abs/1904.02113 · HTML: https://mlsanity.com/paper/1904.02113/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2019.

## Built on by (most cited first, 30 of 42)

- [Spherical Message Passing for 3D Graph Networks](https://mlsanity.com/paper/2102.05013/) (2021)
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://mlsanity.com/paper/2103.01128/) (2021)
- [Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks](https://mlsanity.com/paper/2108.07478/) (2021)
- [Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion](https://mlsanity.com/paper/2103.07074/) (2021)
- [Efficient 3D Semantic Segmentation with Superpoint Transformer](https://mlsanity.com/paper/2306.08045/) (2023)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds](https://mlsanity.com/paper/2111.04426/) (2021)
- [ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution](https://mlsanity.com/paper/2303.00246/) (2023)
- [Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation](https://mlsanity.com/paper/2204.07548/) (2022)
- [PVT: Point-Voxel Transformer for Point Cloud Learning](https://mlsanity.com/paper/2108.06076/) (2021)
- [Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation](https://mlsanity.com/paper/2312.11269/) (2023)
- [Clustering based Point Cloud Representation Learning for 3D Analysis](https://mlsanity.com/paper/2307.14605/) (2023)
- [Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding](https://mlsanity.com/paper/2111.15363/) (2021)
- [Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2107.03601/) (2021)
- [Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients](https://mlsanity.com/paper/2203.15245/) (2022)
- [Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning](https://mlsanity.com/paper/2202.12588/) (2022)
- [SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection](https://mlsanity.com/paper/2312.13641/) (2023)
- [A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2108.09522/) (2021)
- [Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs](https://mlsanity.com/paper/2504.13153/) (2025)
- [A Divide-and-Merge Point Cloud Clustering Algorithm for LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2109.08224/) (2021)
- [MVTN: Learning Multi-View Transformations for 3D Understanding](https://mlsanity.com/paper/2212.13462/) (2022)
- [Region-Enhanced Feature Learning for Scene Semantic Segmentation](https://mlsanity.com/paper/2304.07486/) (2023)
- [PSSNet: Planarity-sensible Semantic Segmentation of Large-scale Urban Meshes](https://mlsanity.com/paper/2202.03209/) (2022)
- [Picasso: A CUDA-based Library for Deep Learning over 3D Meshes](https://mlsanity.com/paper/2103.15076/) (2021)
- [Mesh Convolution with Continuous Filters for 3D Surface Parsing](https://mlsanity.com/paper/2112.01801/) (2021)
- [Upsampling Autoencoder for Self-Supervised Point Cloud Learning](https://mlsanity.com/paper/2203.10768/) (2022)
- [SPNet: Multi-Shell Kernel Convolution for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2109.11610/) (2021)
- [GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation](https://mlsanity.com/paper/2305.15213/) (2023)
- [Generating Unrestricted 3D Adversarial Point Clouds](https://mlsanity.com/paper/2111.08973/) (2021)
- [Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation](https://mlsanity.com/paper/2203.09772/) (2022)

## Abstract (arXiv)

We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents high contrasts. The embeddings are computed using a lightweight neural network operating on the points' local neighborhood. Finally, we formulate point cloud oversegmentation as a graph partition problem with respect to the learned embeddings. This new approach allows us to set a new state-of-the-art in point cloud oversegmentation by a significant margin, on a dense indoor dataset (S3DIS) and a sparse outdoor one (vKITTI). Our best solution requires over five times fewer superpoints to reach similar performance than previously published methods on S3DIS. Furthermore, we show that our framework can be used to improve superpoint-based semantic segmentation algorithms, setting a new state-of-the-art for this task as well.