mlsanityData to 7 Oct 2026

DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection

arXiv 2207.10909 ↗First posted 22 Jul 2022cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Many point-based 3D detectors adopt point-feature sampling strategies to drop some points for efficient inference. These strategies are typically based on fixed and handcrafted rules, making it difficult to handle complicated scenes. Different from them, we propose a Dynamic Ball Query (DBQ) network to adaptively select a subset of input points according to the input features, and assign the feature transform with a suitable receptive field for each selected point. It can be embedded into some state-of-the-art 3D detectors and trained in an end-to-end manner, which significantly reduces the computational cost. Extensive experiments demonstrate that our method can increase the inference speed by 30%-100% on KITTI, Waymo, and ONCE datasets. Specifically, the inference speed of our detector can reach 162 FPS on KITTI scene, and 30 FPS on Waymo and ONCE scenes without performance degradation. Due to skipping the redundant points, some evaluation metrics show significant improvements. Codes will be released at https://github.com/yancie-yjr/DBQ-SSD.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 42 of its 58 references that are in the map. First posted on arXiv 22 Jul 2022.

Builds on

42 of 58 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  5. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  8. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  9. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  10. 2017Deformable Convolutional Networkscited by 1,481
  11. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  12. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
30 more
  1. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  2. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  3. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  4. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  5. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  6. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  7. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  8. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 196
  9. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 185
  10. 2020Resolution Adaptive Networks for Efficient Inferencecited by 146
  11. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  12. 2019IoU Loss for 2D/3D Object Detectioncited by 128
  13. 2019Fast Point R-CNNcited by 119
  14. 2019Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networkscited by 118
  15. 2019TANet: Robust 3D Object Detection from Point Clouds with Triple Attentioncited by 108
  16. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  17. 2019Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inferencecited by 91
  18. 2020Learning Dynamic Routing for Semantic Segmentationcited by 79
  19. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  20. 2020End-to-End Object Detection with Fully Convolutional Networkcited by 70
  21. 2022SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detectioncited by 52
  22. 2021HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detectioncited by 47
  23. 2019TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detectioncited by 36
  24. 2020Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detectioncited by 31
  25. 2022Real-time Object Detection for Streaming Perceptioncited by 29
  26. 2019Learnable Tree Filter for Structure-preserving Feature Transformcited by 25
  27. 2020Fine-Grained Dynamic Head for Object Detectioncited by 16
  28. 20203D IoU-Net: IoU Guided 3D Object Detector for Point Cloudscited by 15
  29. 2020Rethinking Learnable Tree Filter for Generic Feature Transformcited by 10
  30. 2022StreamYOLO: Real-time Object Detection for Streaming Perceptioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 8; 2024: 8; 2025: 4; 2026: 2.

25 papers.

Sort:

By area:

  1. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 245
  2. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  3. 2023Super Sparse 3D Object Detectioncited by 32
  4. 2023Meta-Adapter: An Online Few-shot Learner for Vision-Language Modelcited by 31
  5. 2024SEED: A Simple and Effective 3D DETR in Point Cloudscited by 19
  6. 2022Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Trackingcited by 17
  7. 2025Perspective-Invariant 3D Object Detectioncited by 16
  8. 2024Towards Category Unification of 3D Single Object Tracking on Point Cloudscited by 13
  9. 2024GrootVL: Tree Topology is All You Need in State Space Modelcited by 13
  10. 2023BoxSnake: Polygonal Instance Segmentation with Box Supervisioncited by 12
  11. 2023PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detectioncited by 10
  12. 2023Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detectioncited by 6
13 more
  1. 2023BEVStereo++: Accurate Depth Estimation in Multi-view 3D Object Detection via Dynamic Temporal Stereocited by 4
  2. 2022Towards 3D Object Detection with 2D Supervisioncited by 3
  3. 20233D objects and scenes classification, recognition, segmentation, and reconstruction using 3D point cloud data: A reviewcited by 2
  4. 2022PSA-Det3D: Pillar Set Abstraction for 3D object Detectioncited by 1
  5. 2024AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understandingcited by 1
  6. 2024Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Drivingcited by 1
  7. 2024SGCCNet: Single-Stage 3D Object Detector With Saliency-Guided Data Augmentation and Confidence Correction Mechanismcited by 0
  8. 2024Decoupled and Interactive Regression Modeling for High-performance One-stage 3D Object Detectioncited by 0
  9. 2025PDM-SSD: Single-Stage Three-Dimensional Object Detector With Point Dilationcited by 0
  10. 2025FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object Detectioncited by 0
  11. 2025FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devicescited by 0
  12. 2026Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approachcited by 0
  13. 2026MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detectioncited by 0