mlsanityData to 7 Oct 2026

LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud Segmentation

arXiv 2103.09160 ↗First posted 16 Mar 2021cs.CV cs.AI cs.ROcited by 5

Not on the map. Why?

Abstract (arXiv)

3D point cloud segmentation is an important function that helps robots understand the layout of their surrounding environment and perform tasks such as grasping objects, avoiding obstacles, and finding landmarks. Current segmentation methods are mostly class-specific, many of which are tuned to work with specific object categories and may not be generalizable to different types of scenes. This research proposes a learnable region growing method for class-agnostic point cloud segmentation, specifically for the task of instance label prediction. The proposed method is able to segment any class of objects using a single deep neural network without any assumptions about their shapes and sizes. The deep neural network is trained to predict how to add or remove points from a point cloud region to morph it into incrementally more complete regions of an object instance. Segmentation results on the S3DIS and ScanNet datasets show that the proposed method outperforms competing methods by 1%-9% on 6 different evaluation metrics.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 16 of its 36 references that are in the map. First posted on arXiv 16 Mar 2021.

Builds on

16 of 36 references.

References · 16

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  6. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  7. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  8. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 168
  9. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  10. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 140
  11. 2020Unseen Object Instance Segmentation for Robotic Environmentscited by 85
  12. 2019JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fieldscited by 62
4 more
  1. 2017Learning Heuristic Search via Imitationcited by 34
  2. 20173DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-scale 3D Point Cloudscited by 12
  3. 2019Learning to Optimally Segment Point Cloudscited by 8
  4. 2017A region-growing approach for automatic outcrop fracture extraction from a three-dimensional point cloudcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 0; 2025: 1.

5 papers.

  1. 2023FreePoint: Unsupervised Point Cloud Instance Segmentationcited by 6
  2. 2023ElC-OIS: Ellipsoidal Clustering for Open-World Instance Segmentation on LiDAR Datacited by 3
  3. 2023Analysis of LiDAR Configurations on Off-road Semantic Segmentation Performancecited by 1
  4. 2023Concavity-Induced Distance for Unoriented Point Cloud Decompositioncited by 0
  5. 2025ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentationcited by 0