mlsanityData to 14 Oct 2026

Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds

arXiv 2101.02381 ↗First posted 7 Jan 2021cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects. In this paper, firstly, we propose a Boundary Prediction Module (BPM) to predict boundary points. Based on the predicted boundary, a boundary-aware Geometric Encoding Module (GEM) is designed to encode geometric information and aggregate features with discrimination in a neighborhood, so that the local features belonging to different categories will not be polluted by each other. To provide extra geometric information for boundary-aware GEM, we also propose a light-weight Geometric Convolution Operation (GCO), making the extracted features more distinguishing. Built upon the boundary-aware GEM, we build our network and test it on benchmarks like ScanNet v2, S3DIS. Results show our methods can significantly improve the baseline and achieve state-of-the-art performance. Code is available at https://github.com/JchenXu/BoundaryAwareGEM.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 7 Jan 2021.

Builds on

27 of 34 references.

References · 27

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  11. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  12. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
15 more
  1. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  2. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  3. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  4. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 141
  5. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  6. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  7. 2019Associatively Segmenting Instances and Semantics in Point Cloudscited by 86
  8. 2019Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentationcited by 68
  9. 2019Spherical Kernel for Efficient Graph Convolution on 3D Point Cloudscited by 57
  10. 2018TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshescited by 45
  11. 2020Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentationcited by 40
  12. 2015Semantic Segmentation with Boundary Neural Fieldscited by 37
  13. 2019JSNet: Joint Instance and Semantic Segmentation of 3D Point Cloudscited by 27
  14. 2015High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and its Applications to High-Level Visioncited by 24
  15. 2019Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representationscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 1; 2024: 6; 2025: 6; 2026: 3.

23 papers.

Sort:

  1. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  2. 2021PVT: Point-Voxel Transformer for Point Cloud Learningcited by 43
  3. 2021Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoningcited by 22
  4. 2024Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentationcited by 22
  5. 2024MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selectioncited by 12
  6. 2022GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modelingcited by 8
  7. 2024Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perceptioncited by 8
  8. 20253D Dental Model Segmentation with Geometrical Boundary Preservingcited by 7
  9. 2022Robust Point Cloud Segmentation with Noisy Annotationscited by 6
  10. 2025BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysiscited by 5
  11. 2024ML-SemReg: Boosting Point Cloud Registration with Multi-level Semantic Consistencycited by 4
  12. 2022Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Cloudscited by 3
11 more
  1. 2023SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentationcited by 3
  2. 2024From Easy to Hard: Learning Curricular Shape-aware Features for Robust Panoptic Scene Graph Generationcited by 3
  3. 20223D Intracranial Aneurysm Classification and Segmentation via Unsupervised Dual-branch Learningcited by 1
  4. 2025YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videoscited by 1
  5. 2025Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancycited by 1
  6. 2024DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perceptioncited by 0
  7. 2025EyeSeg: An Uncertainty-Aware Eye Segmentation Framework for AR/VRcited by 0
  8. 2025HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Predictioncited by 0
  9. 2026G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentationcited by 0
  10. 2026World2Minecraft: Occupancy-Driven Simulated Scenes Constructioncited by 0
  11. 2026APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigmscited by 0