mlsanityData to 7 Oct 2026

A Unified Query-based Paradigm for Point Cloud Understanding

arXiv 2203.01252 ↗First posted 2 Mar 2022cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

3D point cloud understanding is an important component in autonomous driving and robotics. In this paper, we present a novel Embedding-Querying paradigm (EQ- Paradigm) for 3D understanding tasks including detection, segmentation, and classification. EQ-Paradigm is a unified paradigm that enables the combination of any existing 3D backbone architectures with different task heads. Under the EQ-Paradigm, the input is firstly encoded in the embedding stage with an arbitrary feature extraction architecture, which is independent of tasks and heads. Then, the querying stage enables the encoded features to be applicable for diverse task heads. This is achieved by introducing an intermediate representation, i.e., Q-representation, in the querying stage to serve as a bridge between the embedding stage and task heads. We design a novel Q- Net as the querying stage network. Extensive experimental results on various 3D tasks, including object detection, semantic segmentation and shape classification, show that EQ-Paradigm in tandem with Q-Net is a general and effective pipeline, which enables a flexible collaboration of backbones and heads, and further boosts the performance of the state-of-the-art methods. Codes and models are available at https://github.com/dvlab-research/DeepVision3D.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 60 of its 75 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

60 of 75 references.

References · 60

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2016Layer Normalizationcited by 5,579
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  10. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  11. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  12. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
38 more
  1. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  2. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2016Pyramid Scene Parsing Networkcited by 2,472
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  8. 2020Point Transformercited by 1,462
  9. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  11. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  12. 2019Objects as Pointscited by 1,172
  13. 2018Self-Attention with Relative Position Representationscited by 1,112
  14. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  15. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  16. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  17. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  18. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  19. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  20. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  21. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  22. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  23. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  24. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  25. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  26. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  27. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  28. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  29. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  30. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  31. 2021Group-Free 3D Object Detection via Transformerscited by 215
  32. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  33. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
  34. 20203D Object Detection with Pointformercited by 194
  35. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  36. 2017Deep Image Mattingcited by 150
  37. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  38. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 13; 2024: 6; 2025: 5; 2026: 3.

32 papers.

Sort:

By area:

  1. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 267
  2. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  3. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 139
  4. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
  5. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  6. 2024Unifying 3D Vision-Language Understanding via Promptable Queriescited by 70
  7. 2023Fully Sparse 3D Occupancy Predictioncited by 61
  8. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  9. 2023V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detectioncited by 34
  10. 2025What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Modelscited by 29
  11. 2022LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformerscited by 21
  12. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
20 more
  1. 2023Point Cloud Classification Using Content-based Transformer via Clustering in Feature Spacecited by 19
  2. 2025LitePT: Lighter Yet Stronger Point Transformercited by 17
  3. 2024KPConvX: Modernizing Kernel Point Convolution with Kernel Attentioncited by 16
  4. 2023Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understandingcited by 13
  5. 2023Unleash the Potential of Image Branch for Cross-modal 3D Object Detectioncited by 11
  6. 2023Uni3DL: Unified Model for 3D and Language Understandingcited by 9
  7. 2023Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentationcited by 6
  8. 2024Improving Distant 3D Object Detection Using 2D Box Supervisioncited by 6
  9. 2024MsSVT++: Mixed-scale Sparse Voxel Transformer with Center Voting for 3D Object Detectioncited by 3
  10. 20223D Harmonic Loss: Towards Task-consistent and Time-friendly 3D Object Detection on Edge for V2X Orchestrationcited by 2
  11. 2023ThermRad: A Multi-modal Dataset for Robust 3D Object Detection under Challenging Conditionscited by 1
  12. 2024Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Drivingcited by 1
  13. 2023Patch-Wise Point Cloud Generation: A Divide-and-Conquer Approachcited by 0
  14. 2024SGCCNet: Single-Stage 3D Object Detector With Saliency-Guided Data Augmentation and Confidence Correction Mechanismcited by 0
  15. 2025FGU3R: Fine-Grained Fusion via Unified 3D Representation for Multimodal 3D Object Detectioncited by 0
  16. 2025PDM-SSD: Single-Stage Three-Dimensional Object Detector With Point Dilationcited by 0
  17. 2025Vision Generalist Model: A Surveycited by 0
  18. 2026Point Virtual Transformercited by 0
  19. 2026Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Predictioncited by 0
  20. 2026From Alignment to Fusion in 3D Vision-Languagecited by 0