# 3D Small Object Detection with Dynamic Spatial Pruning

arXiv: https://arxiv.org/abs/2305.03716 · HTML: https://mlsanity.com/paper/2305.03716/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 60 references that are in the map.
- First posted on arXiv 5 May 2023.

## Builds on (most cited first, 30 of 48)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [Group-Free 3D Object Detection via Transformers](https://mlsanity.com/paper/2104.00678/) (2021)
- [Data-Driven Sparse Structure Selection for Deep Neural Networks](https://mlsanity.com/paper/1707.01213/) (2017)
- [Learning Data Augmentation Strategies for Object Detection](https://mlsanity.com/paper/1906.11172/) (2019)
- [H3DNet: 3D Object Detection Using Hybrid Geometric Primitives](https://mlsanity.com/paper/2006.05682/) (2020)
- [An Analysis of Scale Invariance in Object Detection - SNIP](https://mlsanity.com/paper/1711.08189/) (2017)
- [SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2104.09804/) (2021)
- [FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection](https://mlsanity.com/paper/2112.00322/) (2021)

## Built on by (most cited first, 4 of 4)

- [Embodied Task Planning with Large Language Models](https://mlsanity.com/paper/2307.01848/) (2023)
- [Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning](https://mlsanity.com/paper/2510.11027/) (2025)
- [TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding](https://mlsanity.com/paper/2502.10392/) (2025)
- [Anyview: Generalizable Indoor 3D Object Detection with Variable Frames](https://mlsanity.com/paper/2310.05346/) (2023)

## Abstract (arXiv)

In this paper, we propose an efficient feature pruning strategy for 3D small object detection. Conventional 3D object detection methods struggle on small objects due to the weak geometric information from a small number of points. Although increasing the spatial resolution of feature representations can improve the detection performance on small objects, the additional computational overhead is unaffordable. With in-depth study, we observe the growth of computation mainly comes from the upsampling operation in the decoder of 3D detector. Motivated by this, we present a multi-level 3D detector named DSPDet3D which benefits from high spatial resolution to achieves high accuracy on small object detection, while reducing redundant computation by only focusing on small object areas. Specifically, we theoretically derive a dynamic spatial pruning (DSP) strategy to prune the redundant spatial representation of 3D scene in a cascade manner according to the distribution of objects. Then we design DSP module following this strategy and construct DSPDet3D with this efficient module. On ScanNet and TO-SCENE dataset, our method achieves leading performance on small object detection. Moreover, DSPDet3D trained with only ScanNet rooms can generalize well to scenes in larger scale. It takes less than 2s to directly process a whole building consisting of more than 4500k points while detecting out almost all objects, ranging from cups to beds, on a single RTX 3090 GPU. Project page: https://xuxw98.github.io/DSPDet3D/.