mlsanityData to 7 Oct 2026

SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection

arXiv 2201.01976 ↗First posted 6 Jan 2022cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Although point-based networks are demonstrated to be accurate for 3D point cloud modeling, they are still falling behind their voxel-based competitors in 3D detection. We observe that the prevailing set abstraction design for down-sampling points may maintain too much unimportant background information that can affect feature learning for detecting objects. To tackle this issue, we propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA). Technically, we first add a binary segmentation module as the side output to help identify foreground points. Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling. In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection. Additionally, it is an easy-to-plug-in module and able to boost various point-based detectors, including single-stage and two-stage ones. Extensive experiments on the popular KITTI and nuScenes datasets validate the superiority of SASA, lifting point-based detection models to reach comparable performance to state-of-the-art voxel-based methods.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 27 of its 31 references that are in the map. First posted on arXiv 6 Jan 2022.

Builds on

27 of 31 references.

References · 27

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  7. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  8. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  9. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  10. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  11. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  12. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
15 more
  1. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  2. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  3. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  4. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 196
  5. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  6. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  7. 2019Fast Point R-CNNcited by 119
  8. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  9. 2020Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Thingscited by 110
  10. 2019TANet: Robust 3D Object Detection from Point Clouds with Triple Attentioncited by 108
  11. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  12. 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
  13. 2019Adaptive Hierarchical Down-Sampling for Point Cloud Classificationcited by 40
  14. 2019Progressive LiDAR Adaptation for Road Detectioncited by 37
  15. 2018BirdNet: a 3D Object Detection Framework from LiDAR informationcited by 33

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 14; 2023: 13; 2024: 13; 2025: 10; 2026: 2.

52 papers.

Sort:

By area:

  1. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  2. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  3. 2022Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graphcited by 42
  4. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  5. 2022SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloudcited by 37
  6. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
  7. 2022DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detectioncited by 25
  8. 2022A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attackscited by 22
  9. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  10. 2024SEED: A Simple and Effective 3D DETR in Point Cloudscited by 19
  11. 2023Human-centric Scene Understanding for 3D Large-scale Scenarioscited by 17
  12. 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentationcited by 13
38 more
  1. 2023Unleash the Potential of Image Branch for Cross-modal 3D Object Detectioncited by 11
  2. 2023CP3: Channel Pruning Plug-in for Point-based Networkscited by 10
  3. 2025UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detectioncited by 10
  4. 2022Paint and Distill: Boosting 3D Object Detection with Semantic Passing Networkcited by 7
  5. 2024SparseDet: A Simple and Effective Framework for Fully Sparse LiDAR-based 3D Object Detectioncited by 7
  6. 2024STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learningcited by 6
  7. 2022PointSee: Image Enhances Point Cloudcited by 5
  8. 2024Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Modelscited by 5
  9. 2025GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object Detectorcited by 5
  10. 2023Multi-Modal 3D Object Detection by Box Matchingcited by 4
  11. 2022PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detectioncited by 3
  12. 2024Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?cited by 3
  13. 2025Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Cloudscited by 3
  14. 2025UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNscited by 3
  15. 2023OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML Systemcited by 2
  16. 2023IC-FPS: Instance-Centroid Faster Point Sampling Module for 3D Point-base Object Detectioncited by 2
  17. 2023LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generationcited by 2
  18. 2022SEFormer: Structure Embedding Transformer for 3D Object Detectioncited by 1
  19. 2022PSA-Det3D: Pillar Set Abstraction for 3D object Detectioncited by 1
  20. 2023GeoSpark: Sparking up Point Cloud Segmentation with Geometry Cluecited by 1
  21. 2023Hierarchical Adaptive Voxel-guided Sampling for Real-time Applications in Large-scale Point Cloudscited by 1
  22. 2024LanePtrNet: Revisiting Lane Detection as Point Voting and Grouping on Curvescited by 1
  23. 2024Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Drivingcited by 1
  24. 2024Boosting 3D Object Detection with Semantic-Aware Multi-Branch Frameworkcited by 1
  25. 2024RIDE: Boosting 3D Object Detection for LiDAR Point Clouds via Rotation-Invariant Analysiscited by 1
  26. 2024Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution Alignmentcited by 1
  27. 2022Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain Robustnesscited by 0
  28. 2022Global Hierarchical Attention for 3D Point Cloud Analysiscited by 0
  29. 2022ImLiDAR: Cross-Sensor Dynamic Message Propagation Network for 3D Object Detectioncited by 0
  30. 2023R2Det: Redemption from Range-view for Accurate 3D Object Detectioncited by 0
  31. 2024SGCCNet: Single-Stage 3D Object Detector With Saliency-Guided Data Augmentation and Confidence Correction Mechanismcited by 0
  32. 2024Multi-scale Feature Fusion with Point Pyramid for 3D Object Detectioncited by 0
  33. 2025Intrinsic-feature-guided 3D Object Detectioncited by 0
  34. 2025FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devicescited by 0
  35. 2025Transferable Class Statistics and Multi-scale Feature Approximation for 3D Object Detectioncited by 0
  36. 2025Towards Training-Free Underwater 3D Object Detection from Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approachescited by 0
  37. 2025NV3D: Leveraging Spatial Shape Through Normal Vector-based 3D Object Detectioncited by 0
  38. 2025TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decodercited by 0

50 most cited of 52 All 52 (JSON)