mlsanityData to 14 Oct 2026

Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

arXiv 2105.10203 ↗First posted 21 May 2021cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Hidden features in neural network usually fail to learn informative representation for 3D segmentation as supervisions are only given on output prediction, while this can be solved by omni-scale supervision on intermediate layers. In this paper, we bring the first omni-scale supervision method to point cloud segmentation via the proposed gradual Receptive Field Component Reasoning (RFCR), where target Receptive Field Component Codes (RFCCs) are designed to record categories within receptive fields for hidden units in the encoder. Then, target RFCCs will supervise the decoder to gradually infer the RFCCs in a coarse-to-fine categories reasoning manner, and finally obtain the semantic labels. Because many hidden features are inactive with tiny magnitude and make minor contributions to RFCC prediction, we propose a Feature Densification with a centrifugal potential to obtain more unambiguous features, and it is in effect equivalent to entropy regularization over features. More active features can further unleash the potential of our omni-supervision method. We embed our method into four prevailing backbones and test on three challenging benchmarks. Our method can significantly improve the backbones in all three datasets. Specifically, our method brings new state-of-the-art performances for S3DIS as well as Semantic3D and ranks the 1st in the ScanNet benchmark among all the point-based methods. Code will be publicly available at https://github.com/azuki-miho/RFCR.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 35 of its 44 references that are in the map. First posted on arXiv 21 May 2021.

Builds on

35 of 44 references.

References · 35

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  5. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  6. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  7. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  8. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  9. 2019PointRend: Image Segmentation as Renderingcited by 440
  10. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  11. 2016Convolutional Pose Machinescited by 325
  12. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
23 more
  1. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  2. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  3. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  4. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  5. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  6. 2019Associatively Segmenting Instances and Semantics in Point Cloudscited by 86
  7. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  8. 2019Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentationcited by 68
  9. 2019JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fieldscited by 62
  10. 2020JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Cloudscited by 62
  11. 2019Spherical Kernel for Efficient Graph Convolution on 3D Point Cloudscited by 57
  12. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  13. 2019Region Mutual Information Loss for Semantic Segmentationcited by 49
  14. 2018TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshescited by 45
  15. 2020DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshescited by 42
  16. 2020Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentationcited by 40
  17. 2018Multi-Scale Structure-Aware Network for Human Pose Estimationcited by 37
  18. 2019JSNet: Joint Instance and Semantic Segmentation of 3D Point Cloudscited by 27
  19. 2019Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modelingcited by 25
  20. 2021Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Cloudscited by 23
  21. 2018Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoodscited by 21
  22. 2019Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representationscited by 10
  23. 2020SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptorcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 6; 2024: 3; 2025: 4; 2026: 1.

22 papers.

Sort:

By area:

  1. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  2. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  3. 2023CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentationcited by 12
  4. 2022SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentationcited by 11
  5. 2021HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensorcited by 9
  6. 2024Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perceptioncited by 8
  7. 2023Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentationcited by 6
  8. 2024Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimizationcited by 6
  9. 2022Projection-based Point Convolution for Efficient Point Cloud Segmentationcited by 4
  10. 2023Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scenecited by 4
  11. 2025Fourier Decomposition for Explicit Representation of 3D Point Cloud Attributescited by 4
  12. 2023SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentationcited by 3
10 more
  1. 2021Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusioncited by 1
  2. 20223D Intracranial Aneurysm Classification and Segmentation via Unsupervised Dual-branch Learningcited by 1
  3. 2023Benchmarking Deep Learning Architectures for Urban Vegetation Point Cloud Semantic Segmentation from MLScited by 1
  4. 2023Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignmentcited by 1
  5. 2025YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videoscited by 1
  6. 2025Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learningcited by 1
  7. 2025Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancycited by 1
  8. 2022Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolutioncited by 0
  9. 2024DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perceptioncited by 0
  10. 2026World2Minecraft: Occupancy-Driven Simulated Scenes Constructioncited by 0