# Spatial Pruned Sparse Convolution for Efficient 3D Object Detection

arXiv: https://arxiv.org/abs/2209.14201 · HTML: https://mlsanity.com/paper/2209.14201/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 42 references that are in the map.
- First posted on arXiv 28 Sep 2022.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [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)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [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)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (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)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [Voxel Transformer for 3D Object Detection](https://mlsanity.com/paper/2109.02497/) (2021)
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [Multimodal Virtual Point 3D Detection](https://mlsanity.com/paper/2111.06881/) (2021)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)
- [Focal and Global Knowledge Distillation for Detectors](https://mlsanity.com/paper/2111.11837/) (2021)
- [Focal Sparse Convolutional Networks for 3D Object Detection](https://mlsanity.com/paper/2204.12463/) (2022)
- [CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2012.03015/) (2020)
- [FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection](https://mlsanity.com/paper/2106.12449/) (2021)
- [Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference](https://mlsanity.com/paper/1912.03203/) (2019)
- [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019)
- [Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots](https://mlsanity.com/paper/1912.12791/) (2019)
- [HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection](https://mlsanity.com/paper/2003.00186/) (2020)
- [Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection](https://mlsanity.com/paper/2109.02499/) (2021)
- [More is Less: A More Complicated Network with Less Inference Complexity](https://mlsanity.com/paper/1703.08651/) (2017)

## Built on by (most cited first, 26 of 26)

- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [Spherical Transformer for LiDAR-based 3D Recognition](https://mlsanity.com/paper/2303.12766/) (2023)
- [PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation](https://mlsanity.com/paper/2306.10013/) (2023)
- [SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer](https://mlsanity.com/paper/2303.17605/) (2023)
- [Mask-Attention-Free Transformer for 3D Instance Segmentation](https://mlsanity.com/paper/2309.01692/) (2023)
- [OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation](https://mlsanity.com/paper/2403.14418/) (2024)
- [FastPillars: A Deployment-friendly Pillar-based 3D Detector](https://mlsanity.com/paper/2302.02367/) (2023)
- [LION: Linear Group RNN for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2407.18232/) (2024)
- [Unified Language-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2404.07155/) (2024)
- [ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2303.15334/) (2023)
- [Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement](https://mlsanity.com/paper/2308.03177/) (2023)
- [Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection](https://mlsanity.com/paper/2307.08209/) (2023)
- [STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learning](https://mlsanity.com/paper/2406.19362/) (2024)
- [3D Small Object Detection with Dynamic Spatial Pruning](https://mlsanity.com/paper/2305.03716/) (2023)
- [Sparse Refinement for Efficient High-Resolution Semantic Segmentation](https://mlsanity.com/paper/2407.19014/) (2024)
- [Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection](https://mlsanity.com/paper/2408.13798/) (2024)
- [VALO: A Versatile Anytime Framework for LiDAR-based Object Detection Deep Neural Networks](https://mlsanity.com/paper/2409.11542/) (2024)
- [DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection](https://mlsanity.com/paper/2407.02098/) (2024)
- [Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment](https://mlsanity.com/paper/2312.00663/) (2023)
- [Efficient 3D Perception on Multi-Sweep Point Cloud with Gumbel Spatial Pruning](https://mlsanity.com/paper/2411.07742/) (2024)
- [2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction](https://mlsanity.com/paper/2603.19964/) (2026)
- [AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking](https://mlsanity.com/paper/2409.17728/) (2024)
- [GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2507.20963/) (2025)
- [SUG-Occ: Explicit Semantics and Uncertainty Guided Sparse Learning for Efficient 3D Occupancy Prediction](https://mlsanity.com/paper/2601.11396/) (2026)
- [On Exploring Input Resolution Scaling For Anytime LiDAR Object Detection](https://mlsanity.com/paper/2607.08391/) (2026)
- [ROI-Gated SAHI: Content-Adaptive Slicing-Based Inference for Efficient Object Detection](https://mlsanity.com/paper/2608.23923/) (2026)

## Abstract (arXiv)

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.