# Spatial Pruned Sparse Convolution for Efficient 3D Object Detection

Source: [Spatial Pruned Sparse Convolution for Efficient 3D Object Detection](<https://www.sota2.com/research/paper/68fa6d821e209131cea3a30c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T05:23:16.314Z

Authors: Jianhui Liu, Yukang Chen, Xiaoqing Ye, Zhuotao Tian, Xiao Tan, Xiaojuan Qi

Published: 2022-09-28T16:19:06.000Z

## Abstract

3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyze major components of existing sparse 3D CNNs and find that 3D CNNs ignore the redundancy of data and further amplify it in the down-sampling process, which brings a huge amount of extra and unnecessary computational overhead. Inspired by this, we propose a new convolution operator named spatial pruned sparse convolution (SPS-Conv), which includes two variants, spatial pruned submanifold sparse convolution (SPSS-Conv) and spatial pruned regular sparse convolution (SPRS-Conv), both of which are based on the idea of dynamically determining crucial areas for redundancy reduction. We validate that the magnitude can serve as important cues to determine crucial areas which get rid of the extra computations of learning-based methods. The proposed modules can easily be incorporated into existing sparse 3D CNNs without extra architectural modifications. Extensive experiments on the KITTI, Waymo and nuScenes datasets demonstrate that our method can achieve more than 50% reduction in GFLOPs without compromising the performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Object Detection (Car) on KITTI (val)](<https://www.sota2.com/research/sota/3d-object-detection-car-on-kitti-val.md>): 3D Object Detection (Car); KITTI (val); AP Easy: 89.69.

- [3D Object Detection on nuScenes (test)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-test.md>): 3D Object Detection; nuScenes (test); mAP: 59.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2209.14201>)

[PDF](<https://arxiv.org/pdf/2209.14201.pdf>)