mlsanityData to 14 Oct 2026

KPConvX: Modernizing Kernel Point Convolution with Kernel Attention

arXiv 2405.13194 ↗First posted 21 May 2024cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

In the field of deep point cloud understanding, KPConv is a unique architecture that uses kernel points to locate convolutional weights in space, instead of relying on Multi-Layer Perceptron (MLP) encodings. While it initially achieved success, it has since been surpassed by recent MLP networks that employ updated designs and training strategies. Building upon the kernel point principle, we present two novel designs: KPConvD (depthwise KPConv), a lighter design that enables the use of deeper architectures, and KPConvX, an innovative design that scales the depthwise convolutional weights of KPConvD with kernel attention values. Using KPConvX with a modern architecture and training strategy, we are able to outperform current state-of-the-art approaches on the ScanObjectNN, Scannetv2, and S3DIS datasets. We validate our design choices through ablation studies and release our code and models.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 45 of its 53 references that are in the map. First posted on arXiv 21 May 2024.

Builds on

45 of 53 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2022A ConvNet for the 2020scited by 3,579
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  9. 2020Point Transformercited by 1,470
  10. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  12. 2016Deep Networks with Stochastic Depthcited by 979
33 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  3. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  4. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  5. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  6. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  7. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  8. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  9. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  10. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  11. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  12. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  13. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  14. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  15. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  16. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  17. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  18. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  19. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  20. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  21. 2021Fast Point Transformercited by 104
  22. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99
  23. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  24. 2017Deep Projective 3D Semantic Segmentationcited by 81
  25. 2022LargeKernel3D: Scaling up Kernels in 3D Sparse CNNscited by 72
  26. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  27. 2022Meta Architecture for Point Cloud Analysiscited by 40
  28. 2023Self-positioning Point-based Transformer for Point Cloud Understandingcited by 40
  29. 2022A Unified Query-based Paradigm for Point Cloud Understandingcited by 32
  30. 2022PointConvFormer: Revenge of the Point-based Convolutioncited by 30
  31. 2022PointVector: A Vector Representation In Point Cloud Analysiscited by 21
  32. 2022Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Poolingcited by 9
  33. 2021SPNet: Multi-Shell Kernel Convolution for Point Cloud Semantic Segmentationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 6.

16 papers.

Sort:

By area:

  1. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 110
  2. 2025LitePT: Lighter Yet Stronger Point Transformercited by 17
  3. 2025LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Cloudscited by 8
  4. 2025UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splattingcited by 6
  5. 2025No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weathercited by 5
  6. 2026Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understandingcited by 4
  7. 2025PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentationcited by 2
  8. 2025RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completioncited by 1
  9. 2025Late-decoupled 3D Hierarchical Semantic Segmentation with Semantic Prototype Discrimination based Bi-branch Supervisioncited by 1
  10. 2026PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learningcited by 1
  11. 2025An Experimental Study of SOTA LiDAR Segmentation Modelscited by 0
  12. 2025Deep Imbalanced Multi-Target Regression: 3D Point Cloud Voxel Content Estimation in Simulated Forestscited by 0
4 more
  1. 2026Learning Coordinate-based Convolutional Kernels for Continuous SE(3) Equivariant and Efficient Point Cloud Analysiscited by 0
  2. 2026From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environmentscited by 0
  3. 2026Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysiscited by 0
  4. 2026PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectificationcited by 0