mlsanityData to 14 Oct 2026

Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes

arXiv 2208.06671 ↗First posted 13 Aug 2022cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Few-shot segmentation of point cloud remains a challenging task, as there is no effective way to convert local point cloud information to global representation, which hinders the generalization ability of point features. In this study, we propose a bidirectional feature globalization (BFG) approach, which leverages the similarity measurement between point features and prototype vectors to embed global perception to local point features in a bidirectional fashion. With point-to-prototype globalization (Po2PrG), BFG aggregates local point features to prototypes according to similarity weights from dense point features to sparse prototypes. With prototype-to-point globalization (Pr2PoG), the global perception is embedded to local point features based on similarity weights from sparse prototypes to dense point features. The sparse prototypes of each class embedded with global perception are summarized to a single prototype for few-shot 3D segmentation based on the metric learning framework. Extensive experiments on S3DIS and ScanNet demonstrate that BFG significantly outperforms the state-of-the-art methods.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 13 Aug 2022.

Builds on

25 of 34 references.

References · 25

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  8. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  11. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  12. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
13 more
  1. 2017One-Shot Learning for Semantic Segmentationcited by 337
  2. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  3. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  4. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  5. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  6. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  7. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  8. 2018Superpixel Sampling Networkscited by 79
  9. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  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. 2022Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classificationcited by 16
  13. 2022Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoderscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 10; 2025: 6; 2026: 1.

23 papers.

Sort:

By area:

  1. 2024Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentationcited by 20
  2. 2024Rethinking Few-shot 3D Point Cloud Semantic Segmentationcited by 18
  3. 2024No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentationcited by 18
  4. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  5. 2025Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentationcited by 14
  6. 2022Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detectioncited by 12
  7. 2023Generalized Few-Shot Point Cloud Segmentation Via Geometric Wordscited by 12
  8. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11
  9. 2023Not Just Learning from Others but Relying on Yourself: A New Perspective on Few-Shot Segmentation in Remote Sensingcited by 11
  10. 2024Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentationcited by 10
  11. 2025AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Featurescited by 9
  12. 2024AgMTR: Agent Mining Transformer for Few-shot Segmentation in Remote Sensingcited by 6
11 more
  1. 2024MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototypingcited by 5
  2. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  3. 2023Towards Robust Few-shot Point Cloud Semantic Segmentationcited by 3
  4. 2024SDL-MVS: View Space and Depth Deformable Learning Paradigm for Multi-View Stereo Reconstruction in Remote Sensingcited by 3
  5. 2023Self-guided Few-shot Semantic Segmentation for Remote Sensing Imagery Based on Large Vision Modelscited by 2
  6. 2024TAFormer: A Unified Target-Aware Transformer for Video and Motion Joint Prediction in Aerial Scenescited by 2
  7. 2026SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentationcited by 1
  8. 2024Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentationcited by 0
  9. 2024UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registrationcited by 0
  10. 2025Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentationcited by 0
  11. 2025Query-aware Hub Prototype Learning for Few-Shot 3D Point Cloud Semantic Segmentationcited by 0