mlsanityData to 7 Oct 2026

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds

arXiv 2210.04264 ↗First posted 9 Oct 2022cs.CVcited by 58

Not on the map. Why?

Abstract (arXiv)

We present a novel two-stage fully sparse convolutional 3D object detection framework, named CAGroup3D. Our proposed method first generates some high-quality 3D proposals by leveraging the class-aware local group strategy on the object surface voxels with the same semantic predictions, which considers semantic consistency and diverse locality abandoned in previous bottom-up approaches. Then, to recover the features of missed voxels due to incorrect voxel-wise segmentation, we build a fully sparse convolutional RoI pooling module to directly aggregate fine-grained spatial information from backbone for further proposal refinement. It is memory-and-computation efficient and can better encode the geometry-specific features of each 3D proposal. Our model achieves state-of-the-art 3D detection performance with remarkable gains of +textit3.6% on ScanNet V2 and +textit2.6% on SUN RGB-D in term of [email protected]. Code will be available at https://github.com/Haiyang-W/CAGroup3D.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). Builds on 47 of its 65 references that are in the map. First posted on arXiv 9 Oct 2022.

Builds on

47 of 65 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  7. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  10. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  11. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  12. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
35 more
  1. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  2. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  3. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  4. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  5. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  6. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  7. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  8. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  9. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  10. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  11. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  12. 2017Submanifold Sparse Convolutional Networkscited by 223
  13. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
  14. 2021Group-Free 3D Object Detection via Transformerscited by 215
  15. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
  16. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  17. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 145
  18. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 140
  19. 2022Multimodal Token Fusion for Vision Transformerscited by 132
  20. 2020H3DNet: 3D Object Detection Using Hybrid Geometric Primitivescited by 123
  21. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  22. 2021FCAF3D: Fully Convolutional Anchor-Free 3D Object Detectioncited by 97
  23. 2021Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenescited by 89
  24. 2020Improved Analysis of Clipping Algorithms for Non-convex Optimizationcited by 88
  25. 2020MLCVNet: Multi-Level Context VoteNet for 3D Object Detectioncited by 80
  26. 2020Generative Sparse Detection Networks for 3D Single-shot Object Detectioncited by 69
  27. 2021Back-tracing Representative Points for Voting-based 3D Object Detection in Point Cloudscited by 67
  28. 2022RBGNet: Ray-based Grouping for 3D Object Detectioncited by 40
  29. 2021Non-convex Distributionally Robust Optimization: Non-asymptotic Analysiscited by 39
  30. 2019Monocular Plan View Networks for Autonomous Drivingcited by 37
  31. 2020InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modelingcited by 35
  32. 2021Collaborative Visual Navigationcited by 18
  33. 2022HyperDet3D: Learning a Scene-conditioned 3D Object Detectorcited by 14
  34. 2022FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detectioncited by 14
  35. 2022Boosting 3D Object Detection via Object-Focused Image Fusioncited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 22; 2024: 24; 2025: 5; 2026: 6.

58 papers.

Sort:

By area:

  1. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  2. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  3. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  4. 2023OneFormer3D: One Transformer for Unified Point Cloud Segmentationcited by 95
  5. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  6. 2025SpatialLM: Training Large Language Models for Structured Indoor Modelingcited by 63
  7. 2023NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detectioncited by 51
  8. 2023Point Cloud Pre-training with Diffusion Modelscited by 47
  9. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  10. 2024EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understandingcited by 43
  11. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  12. 2023V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detectioncited by 34
38 more
  1. 2023Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Modelscited by 26
  2. 2023Uni3DETR: Unified 3D Detection Transformercited by 26
  3. 2024OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagationcited by 19
  4. 2022EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encodercited by 18
  5. 2023DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detectioncited by 16
  6. 2023ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understandingcited by 16
  7. 2023Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detectioncited by 14
  8. 2024Towards Category Unification of 3D Single Object Tracking on Point Cloudscited by 13
  9. 20243DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for Indoor 3D Object Detectioncited by 13
  10. 2024SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentationcited by 12
  11. 2023Uni3DL: Unified Model for 3D and Language Understandingcited by 9
  12. 2024Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object Detectioncited by 9
  13. 2024PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Modelscited by 9
  14. 2024BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentationcited by 9
  15. 2024ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Imagescited by 9
  16. 2024One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detectioncited by 8
  17. 2023PRED: Pre-training via Semantic Rendering on LiDAR Point Cloudscited by 7
  18. 2024Diff3DETR:Agent-based Diffusion Model for Semi-supervised 3D Object Detectioncited by 7
  19. 2024Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understandingcited by 6
  20. 2024Towards Unified 3D Object Detection via Algorithm and Data Unificationcited by 6
  21. 2024Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detectioncited by 6
  22. 2023Fine-grained Text and Image Guided Point Cloud Completion with CLIP Modelcited by 5
  23. 2023LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Datasetcited by 5
  24. 2025State Space Model Meets Transformer: A New Paradigm for 3D Object Detectioncited by 5
  25. 20233D Small Object Detection with Dynamic Spatial Pruningcited by 4
  26. 2024NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detectioncited by 4
  27. 2025Sketchy Bounding-box Supervision for 3D Instance Segmentationcited by 4
  28. 2023Multi-View Representation is What You Need for Point-Cloud Pre-Trainingcited by 3
  29. 2024MsSVT++: Mixed-scale Sparse Voxel Transformer with Center Voting for 3D Object Detectioncited by 3
  30. 20243D Object Detection from Point Cloud via Voting Step Diffusioncited by 3
  31. 2024SAM-Guided Masked Token Prediction for 3D Scene Understandingcited by 3
  32. 2025UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNscited by 3
  33. 2024NeRF-DetS: Enhanced Adaptive Spatial-wise Sampling and View-wise Fusion Strategies for NeRF-based Indoor Multi-view 3D Object Detectioncited by 2
  34. 2025PointSplit: Towards On-device 3D Object Detection with Heterogeneous Low-power Acceleratorscited by 2
  35. 2026Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environmentscited by 2
  36. 2023Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysiscited by 1
  37. 2024CascadeV-Det: Cascade Point Voting for 3D Object Detectioncited by 1
  38. 2024Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Drivingcited by 1

50 most cited of 58 All 58 (JSON)