mlsanityData to 14 Oct 2026

Projection-based Point Convolution for Efficient Point Cloud Segmentation

arXiv 2202.01991 ↗First posted 4 Feb 2022cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Understanding point cloud has recently gained huge interests following the development of 3D scanning devices and the accumulation of large-scale 3D data. Most point cloud processing algorithms can be classified as either point-based or voxel-based methods, both of which have severe limitations in processing time or memory, or both. To overcome these limitations, we propose Projection-based Point Convolution (PPConv), a point convolutional module that uses 2D convolutions and multi-layer perceptrons (MLPs) as its components. In PPConv, point features are processed through two branches: point branch and projection branch. Point branch consists of MLPs, while projection branch transforms point features into a 2D feature map and then apply 2D convolutions. As PPConv does not use point-based or voxel-based convolutions, it has advantages in fast point cloud processing. When combined with a learnable projection and effective feature fusion strategy, PPConv achieves superior efficiency compared to state-of-the-art methods, even with a simple architecture based on PointNet++. We demonstrate the efficiency of PPConv in terms of the trade-off between inference time and segmentation performance. The experimental results on S3DIS and ShapeNetPart show that PPConv is the most efficient method among the compared ones. The code is available at github.com/pahn04/PPConv.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 43 of its 55 references that are in the map. First posted on arXiv 4 Feb 2022.

Builds on

43 of 55 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  10. 2020Point Transformercited by 1,470
  11. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  12. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
31 more
  1. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 2020Convolutional Occupancy Networkscited by 761
  4. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  5. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  8. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  9. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  10. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  11. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  12. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  13. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  14. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  15. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  16. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  17. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  18. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  19. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  20. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  21. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  22. 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
  23. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  24. 2017Deep Projective 3D Semantic Segmentationcited by 81
  25. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 72
  26. 2016SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentationcited by 70
  27. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  28. 2020End-to-End Learning Local Multi-view Descriptors for 3D Point Cloudscited by 47
  29. 2020Dynamic Plane Convolutional Occupancy Networkscited by 24
  30. 2021Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoningcited by 22
  31. 2020PBP-Net: Point Projection and Back-Projection Network for 3D Point Cloud Segmentationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2025Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNetcited by 3
  2. 2025SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformitycited by 1
  3. 2026NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentationcited by 1
  4. 2024Region-Transformer: Self-Attention Region Based Class-Agnostic Point Cloud Segmentationcited by 0