# Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization

arXiv: https://arxiv.org/abs/2207.11209 · HTML: https://mlsanity.com/paper/2207.11209/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 58 references that are in the map.
- First posted on arXiv 22 Jul 2022.

## Builds on (most cited first, 30 of 46)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans](https://mlsanity.com/paper/1812.07003/) (2018)
- [K-Net: Towards Unified Image Segmentation](https://mlsanity.com/paper/2106.14855/) (2021)
- [OccuSeg: Occupancy-aware 3D Instance Segmentation](https://mlsanity.com/paper/2003.06537/) (2020)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation](https://mlsanity.com/paper/1711.08588/) (2017)
- [Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/1906.01140/) (2019)
- [GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud](https://mlsanity.com/paper/1812.03320/) (2018)
- [3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2003.13867/) (2020)
- [Hierarchical Aggregation for 3D Instance Segmentation](https://mlsanity.com/paper/2108.02350/) (2021)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation](https://mlsanity.com/paper/1803.10409/) (2018)

## Built on by (most cited first, 26 of 26)

- [OneFormer3D: One Transformer for Unified Point Cloud Segmentation](https://mlsanity.com/paper/2311.14405/) (2023)
- [ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution](https://mlsanity.com/paper/2303.00246/) (2023)
- [PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection](https://mlsanity.com/paper/2412.12617/) (2024)
- [DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering](https://mlsanity.com/paper/2410.13607/) (2024)
- [ODIN: A Single Model for 2D and 3D Segmentation](https://mlsanity.com/paper/2401.02416/) (2024)
- [Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation](https://mlsanity.com/paper/2312.11269/) (2023)
- [ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation](https://mlsanity.com/paper/2311.14262/) (2023)
- [A Unified Framework for 3D Scene Understanding](https://mlsanity.com/paper/2407.03263/) (2024)
- [SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation](https://mlsanity.com/paper/2407.11564/) (2024)
- [BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis](https://mlsanity.com/paper/2503.12539/) (2025)
- [Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges](https://mlsanity.com/paper/2312.07039/) (2023)
- [MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation](https://mlsanity.com/paper/2411.01781/) (2024)
- [All in One: Visual-Description-Guided Unified Point Cloud Segmentation](https://mlsanity.com/paper/2507.05211/) (2025)
- [Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation](https://mlsanity.com/paper/2212.06682/) (2022)
- [A boundary-aware point clustering approach in Euclidean and embedding spaces for roof plane segmentation](https://mlsanity.com/paper/2309.03722/) (2023)
- [Zero-Shot Dual-Path Integration Framework for Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2408.08591/) (2024)
- [LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation](https://mlsanity.com/paper/2602.11007/) (2026)
- [HOMER: Homography-Based Efficient Multi-view 3D Object Removal](https://mlsanity.com/paper/2501.17636/) (2025)
- [EipFormer: Emphasizing Instance Positions in 3D Instance Segmentation](https://mlsanity.com/paper/2312.05602/) (2023)
- [GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2510.02186/) (2025)
- [StrokeNet: Unveiling How to Learn Fine-Grained Interactions in Online Handwritten Stroke Classification](https://mlsanity.com/paper/2512.06290/) (2025)
- [PSGformer: Enhancing 3D Point Cloud Instance Segmentation via Precise Semantic Guidance](https://mlsanity.com/paper/2307.07708/) (2023)
- [3D-CDRGP: Towards Cross-Device Robotic Grasping Policy in 3D Open World](https://mlsanity.com/paper/2411.18133/) (2024)
- [Towards Training-Free Open-World Classification with 3D Generative Models](https://mlsanity.com/paper/2501.17547/) (2025)
- [MSMA: Multi-Scale Feature Fusion For Multi-Attribute 3D Face Reconstruction From Unconstrained Images](https://mlsanity.com/paper/2509.11763/) (2025)
- [DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2511.10003/) (2025)

## Abstract (arXiv)

Instance segmentation on point clouds is crucially important for 3D scene understanding. Most SOTAs adopt distance clustering, which is typically effective but does not perform well in segmenting adjacent objects with the same semantic label (especially when they share neighboring points). Due to the uneven distribution of offset points, these existing methods can hardly cluster all instance points. To this end, we design a novel divide-and-conquer strategy named PBNet that binarizes each point and clusters them separately to segment instances. Our binary clustering divides offset instance points into two categories: high and low density points (HPs vs. LPs). Adjacent objects can be clearly separated by removing LPs, and then be completed and refined by assigning LPs via a neighbor voting method. To suppress potential over-segmentation, we propose to construct local scenes with the weight mask for each instance. As a plug-in, the proposed binary clustering can replace traditional distance clustering and lead to consistent performance gains on many mainstream baselines. A series of experiments on ScanNetV2 and S3DIS datasets indicate the superiority of our model. In particular, PBNet ranks first on the ScanNetV2 official benchmark challenge, achieving the highest mAP. Code will be available publicly at https://github.com/weiguangzhao/PBNet.