mlsanityData to 7 Oct 2026

GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds

arXiv 2109.11835 ↗First posted 24 Sep 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

An efficient solution to semantic segmentation of large-scale indoor scene point clouds is proposed in this work. It is named GSIP (Green Segmentation of Indoor Point clouds) and its performance is evaluated on a representative large-scale benchmark -- the Stanford 3D Indoor Segmentation (S3DIS) dataset. GSIP has two novel components: 1) a room-style data pre-processing method that selects a proper subset of points for further processing, and 2) a new feature extractor which is extended from PointHop. For the former, sampled points of each room form an input unit. For the latter, the weaknesses of PointHop's feature extraction when extending it to large-scale point clouds are identified and fixed with a simpler processing pipeline. As compared with PointNet, which is a pioneering deep-learning-based solution, GSIP is green since it has significantly lower computational complexity and a much smaller model size. Furthermore, experiments show that GSIP outperforms PointNet in segmentation performance for the S3DIS dataset.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 25 of its 39 references that are in the map. First posted on arXiv 24 Sep 2021.

Builds on

25 of 39 references.

References · 25

  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. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 2020PCT: Point cloud transformercited by 730
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  7. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  8. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  9. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  10. 2018PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentationcited by 58
  11. 2018Interpretable Convolutional Neural Networks via Feedforward Designcited by 49
  12. 2019PointHop: An Explainable Machine Learning Method for Point Cloud Classificationcited by 46
13 more
  1. 2018Fully-Convolutional Point Networks for Large-Scale Point Cloudscited by 44
  2. 2020PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classificationcited by 37
  3. 2016Understanding Convolutional Neural Networks with A Mathematical Modelcited by 33
  4. 2021DefakeHop: A Light-Weight High-Performance Deepfake Detectorcited by 31
  5. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  6. 2017On Data-Driven Saak Transformcited by 22
  7. 2020PointHop++: A Lightweight Learning Model on Point Sets for 3D Classificationcited by 22
  8. 2020Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)cited by 19
  9. 2020Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentationcited by 17
  10. 2020FaceHop: A Light-Weight Low-Resolution Face Gender Classification Methodcited by 16
  11. 2021AnomalyHop: An SSL-based Image Anomaly Localization Methodcited by 12
  12. 2021E-PixelHop: An Enhanced PixelHop Method for Object Classificationcited by 9
  13. 2017A Saak Transform Approach to Efficient, Scalable and Robust Handwritten Digits Recognitioncited by 7

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 4.

7 papers.

  1. 2022Green Learning: Introduction, Examples and Outlookcited by 30
  2. 2022PAGER: Progressive Attribute-Guided Extendable Robust Image Generationcited by 5
  3. 2021GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Methodcited by 4
  4. 2023S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classificationcited by 3
  5. 2023Enhancing Edge Intelligence with Highly Discriminant LNT Featurescited by 3
  6. 2023PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Cloudscited by 1
  7. 2023A Tiny Machine Learning Model for Point Cloud Object Classificationcited by 0