mlsanityData to 7 Oct 2026

DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion

arXiv 2111.10332 ↗First posted 19 Nov 2021cs.CV cs.AI cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Point cloud processing is a challenging task due to its sparsity and irregularity. Prior works introduce delicate designs on either local feature aggregator or global geometric architecture, but few combine both advantages. We propose Dual-Scale Point Cloud Recognition with High-frequency Fusion (DSPoint) to extract local-global features by concurrently operating on voxels and points. We reverse the conventional design of applying convolution on voxels and attention to points. Specifically, we disentangle point features through channel dimension for dual-scale processing: one by point-wise convolution for fine-grained geometry parsing, the other by voxel-wise global attention for long-range structural exploration. We design a co-attention fusion module for feature alignment to blend local-global modalities, which conducts inter-scale cross-modality interaction by communicating high-frequency coordinates information. Experiments and ablations on widely-adopted ModelNet40, ShapeNet, and S3DIS demonstrate the state-of-the-art performance of our DSPoint.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 19 Nov 2021.

Builds on

40 of 57 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2020Point Transformercited by 1,462
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  12. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
28 more
  1. 2020PCT: Point cloud transformercited by 730
  2. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  3. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  4. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  5. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  6. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  7. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  8. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  9. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  10. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  11. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  12. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  13. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  14. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  15. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  16. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  17. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  18. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  19. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  20. 2019Monocular 3D Object Detection with Pseudo-LiDAR Point Cloudcited by 113
  21. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  22. 2016SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentationcited by 70
  23. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  24. 2021Dual-stream Network for Visual Recognitioncited by 33
  25. 2021Lidar Point Cloud Guided Monocular 3D Object Detectioncited by 29
  26. 20143D ShapeNets: A Deep Representation for Volumetric Shapescited by 27
  27. 2021Dual Transformer for Point Cloud Analysiscited by 26
  28. 2018Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networkscited by 9

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 6; 2024: 7; 2025: 2.

17 papers.

Sort:

  1. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  2. 2024Binding Touch to Everything: Learning Unified Multimodal Tactile Representationscited by 94
  3. 2023ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidancecited by 70
  4. 2023Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networkscited by 54
  5. 2023Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-trainingcited by 52
  6. 2023Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysiscited by 34
  7. 2024WorDepth: Variational Language Prior for Monocular Depth Estimationcited by 34
  8. 2024RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptionscited by 20
  9. 2024NeuroBind: Towards Unified Multimodal Representations for Neural Signalscited by 13
  10. 2024Style Transfer: From Stitching to Neural Networkscited by 8
  11. 2023Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentationcited by 5
  12. 2023Nearest Neighbors Meet Deep Neural Networks for Point Cloud Analysiscited by 5
5 more
  1. 2022PointNorm: Dual Normalization is All You Need for Point Cloud Analysiscited by 3
  2. 2024SP2T: Sparse Proxy Attention for Dual-stream Point Transformercited by 3
  3. 2024Enhancing Exchange Rate Forecasting with Explainable Deep Learning Modelscited by 2
  4. 2025HOMER: Homography-Based Efficient Multi-view 3D Object Removalcited by 2
  5. 2025Mesh RAG: Retrieval Augmentation for Autoregressive Mesh Generationcited by 0