3D Small Object Detection with Dynamic Spatial Pruning

TL;DR

This paper introduces DSPDet3D, a 3D object detection method that employs dynamic spatial pruning to efficiently detect small objects by reducing redundant computations, achieving high accuracy with less processing time.

Contribution

The paper proposes a novel dynamic spatial pruning strategy and integrates it into a multi-level 3D detector, significantly improving small object detection efficiency and accuracy.

Findings

Achieves leading performance on ScanNet and TO-SCENE datasets.

Processes large scenes in less than 2 seconds on a single GPU.

Generalizes well from small-scale to large-scale scenes.

Abstract

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/.