mlsanityData to 7 Oct 2026

Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud

arXiv 2103.10339 ↗First posted 18 Mar 2021cs.CV eess.IVcited by 6

Not on the map. Why?

Abstract (arXiv)

This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds. The indistinguishable points consist of those located in complex boundary, points with similar local textures but different categories, and points in isolate small hard areas, which largely harm the performance of 3D semantic segmentation. To address this challenge, we propose a novel Indistinguishable Area Focalization Network (IAF-Net), which selects indistinguishable points adaptively by utilizing the hierarchical semantic features and enhances fine-grained features for points especially those indistinguishable points. We also introduce multi-stage loss to improve the feature representation in a progressive way. Moreover, in order to analyze the segmentation performances of indistinguishable areas, we propose a new evaluation metric called Indistinguishable Points Based Metric (IPBM). Our IAF-Net achieves the comparable results with state-of-the-art performance on several popular 3D point cloud datasets e.g. S3DIS and ScanNet, and clearly outperforms other methods on IPBM.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 18 Mar 2021.

Builds on

28 of 35 references.

References · 28

  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. 2017Non-local Neural Networkscited by 2,290
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  7. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  8. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  11. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  12. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
16 more
  1. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  2. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  3. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  4. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  5. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  6. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  7. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  8. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  9. 2019A-CNN: Annularly Convolutional Neural Networks on Point Cloudscited by 66
  10. 2019ConvPoint: Continuous Convolutions for Point Cloud Processingcited by 62
  11. 2018PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentationcited by 58
  12. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  13. 2017Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascadecited by 53
  14. 2019Geometry Sharing Network for 3D Point Cloud Classification and Segmentationcited by 33
  15. 2019Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modelingcited by 25
  16. 2019LassoNet: Deep Lasso-Selection of 3D Point Cloudscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 0; 2024: 0; 2025: 0; 2026: 1.

6 papers.

  1. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  2. 2021PVT: Point-Voxel Transformer for Point Cloud Learningcited by 42
  3. 2022MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistencycited by 12
  4. 2022GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modelingcited by 8
  5. 2022Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Cloudscited by 3
  6. 2026G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentationcited by 0