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

arXiv: https://arxiv.org/abs/2207.10909 · HTML: https://mlsanity.com/paper/2207.10909/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 58 references that are in the map.
- First posted on arXiv 22 Jul 2022.

## Builds on (most cited first, 30 of 42)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://mlsanity.com/paper/1907.03670/) (2019)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [One Million Scenes for Autonomous Driving: ONCE Dataset](https://mlsanity.com/paper/2106.11037/) (2021)
- [Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates](https://mlsanity.com/paper/1708.07120/) (2017)
- [BlockDrop: Dynamic Inference Paths in Residual Networks](https://mlsanity.com/paper/1711.08393/) (2017)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [IoU Loss for 2D/3D Object Detection](https://mlsanity.com/paper/1908.03851/) (2019)
- [Fast Point R-CNN](https://mlsanity.com/paper/1908.02990/) (2019)
- [Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1909.08174/) (2019)
- [TANet: Robust 3D Object Detection from Point Clouds with Triple Attention](https://mlsanity.com/paper/1912.05163/) (2019)
- [CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2012.03015/) (2020)
- [Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference](https://mlsanity.com/paper/1912.03203/) (2019)
- [Learning Dynamic Routing for Semantic Segmentation](https://mlsanity.com/paper/2003.10401/) (2020)

## Built on by (most cited first, 25 of 25)

- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [LION: Linear Group RNN for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2407.18232/) (2024)
- [Super Sparse 3D Object Detection](https://mlsanity.com/paper/2301.02562/) (2023)
- [Meta-Adapter: An Online Few-shot Learner for Vision-Language Model](https://mlsanity.com/paper/2311.03774/) (2023)
- [SEED: A Simple and Effective 3D DETR in Point Clouds](https://mlsanity.com/paper/2407.10749/) (2024)
- [Perspective-Invariant 3D Object Detection](https://mlsanity.com/paper/2507.17665/) (2025)
- [Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking](https://mlsanity.com/paper/2208.10976/) (2022)
- [Towards Category Unification of 3D Single Object Tracking on Point Clouds](https://mlsanity.com/paper/2401.11204/) (2024)
- [GrootVL: Tree Topology is All You Need in State Space Model](https://mlsanity.com/paper/2406.02395/) (2024)
- [BoxSnake: Polygonal Instance Segmentation with Box Supervision](https://mlsanity.com/paper/2303.11630/) (2023)
- [PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection](https://mlsanity.com/paper/2311.17770/) (2023)
- [Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection](https://mlsanity.com/paper/2307.08209/) (2023)
- [BEVStereo++: Accurate Depth Estimation in Multi-view 3D Object Detection via Dynamic Temporal Stereo](https://mlsanity.com/paper/2304.04185/) (2023)
- [Towards 3D Object Detection with 2D Supervision](https://mlsanity.com/paper/2211.08287/) (2022)
- [3D objects and scenes classification, recognition, segmentation, and reconstruction using 3D point cloud data: A review](https://mlsanity.com/paper/2306.05978/) (2023)
- [PSA-Det3D: Pillar Set Abstraction for 3D object Detection](https://mlsanity.com/paper/2210.10983/) (2022)
- [AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding](https://mlsanity.com/paper/2402.17521/) (2024)
- [Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2403.06166/) (2024)
- [SGCCNet: Single-Stage 3D Object Detector With Saliency-Guided Data Augmentation and Confidence Correction Mechanism](https://mlsanity.com/paper/2407.01239/) (2024)
- [Decoupled and Interactive Regression Modeling for High-performance One-stage 3D Object Detection](https://mlsanity.com/paper/2409.00690/) (2024)
- [PDM-SSD: Single-Stage Three-Dimensional Object Detector With Point Dilation](https://mlsanity.com/paper/2502.07822/) (2025)
- [FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object Detection](https://mlsanity.com/paper/2503.01899/) (2025)
- [FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices](https://mlsanity.com/paper/2506.04499/) (2025)
- [Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach](https://mlsanity.com/paper/2605.14601/) (2026)
- [MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection](https://mlsanity.com/paper/2608.14282/) (2026)

## 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.