# Efficient 3D Perception on Multi-Sweep Point Cloud with Gumbel Spatial Pruning

arXiv: https://arxiv.org/abs/2411.07742 · HTML: https://mlsanity.com/paper/2411.07742/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 12 Nov 2024.

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

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2203.08195/) (2022)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/1910.06528/) (2019)
- [PointMamba: A Simple State Space Model for Point Cloud Analysis](https://mlsanity.com/paper/2402.10739/) (2024)
- [Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation](https://mlsanity.com/paper/2103.14962/) (2021)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2207.10035/) (2022)
- [M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers](https://mlsanity.com/paper/2104.11896/) (2021)
- [TorchSparse: Efficient Point Cloud Inference Engine](https://mlsanity.com/paper/2204.10319/) (2022)
- [LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs](https://mlsanity.com/paper/2206.10555/) (2022)
- [MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection](https://mlsanity.com/paper/2209.03102/) (2022)
- [HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2310.20234/) (2023)
- [Uni3DETR: Unified 3D Detection Transformer](https://mlsanity.com/paper/2310.05699/) (2023)
- [Spatial Pruned Sparse Convolution for Efficient 3D Object Detection](https://mlsanity.com/paper/2209.14201/) (2022)
- [LinK: Linear Kernel for LiDAR-based 3D Perception](https://mlsanity.com/paper/2303.16094/) (2023)
- [MVGamba: Unify 3D Content Generation as State Space Sequence Modeling](https://mlsanity.com/paper/2406.06367/) (2024)
- [AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset](https://mlsanity.com/paper/2306.00612/) (2023)
- [MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds](https://mlsanity.com/paper/2212.07207/) (2022)
- [Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition](https://mlsanity.com/paper/2308.09694/) (2023)
- [MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Driving](https://mlsanity.com/paper/2309.16715/) (2023)

## Built on by (most cited first, 1 of 1)

- [MVAnimate: Enhancing Character Animation with Multi-View Optimization](https://mlsanity.com/paper/2602.08753/) (2026)

## Abstract (arXiv)

This paper studies point cloud perception within outdoor environments. Existing methods face limitations in recognizing objects located at a distance or occluded, due to the sparse nature of outdoor point clouds. In this work, we observe a significant mitigation of this problem by accumulating multiple temporally consecutive point cloud sweeps, resulting in a remarkable improvement in perception accuracy. However, the computation cost also increases, hindering previous approaches from utilizing a large number of point cloud sweeps. To tackle this challenge, we find that a considerable portion of points in the accumulated point cloud is redundant, and discarding these points has minimal impact on perception accuracy. We introduce a simple yet effective Gumbel Spatial Pruning (GSP) layer that dynamically prunes points based on a learned end-to-end sampling. The GSP layer is decoupled from other network components and thus can be seamlessly integrated into existing point cloud network architectures. Without incurring additional computational overhead, we increase the number of point cloud sweeps from 10, a common practice, to as many as 40. Consequently, there is a significant enhancement in perception performance. For instance, in nuScenes 3D object detection and BEV map segmentation tasks, our pruning strategy improves several 3D perception baseline methods.