# Point Cloud Segmentation Using Sparse Temporal Local Attention

arXiv: https://arxiv.org/abs/2112.00289 · HTML: https://mlsanity.com/paper/2112.00289/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 46 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 30 of 34)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [SEGCloud: Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1710.07563/) (2017)
- [Tangent Convolutions for Dense Prediction in 3D](https://mlsanity.com/paper/1807.02443/) (2018)
- [SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation](https://mlsanity.com/paper/2004.01803/) (2020)
- [Improving Semantic Segmentation via Video Propagation and Label Relaxation](https://mlsanity.com/paper/1812.01593/) (2018)
- [Pointwise Convolutional Neural Networks](https://mlsanity.com/paper/1712.05245/) (2017)
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/1910.09165/) (2019)
- [Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video](https://mlsanity.com/paper/1807.06667/) (2018)
- [Temporally Distributed Networks for Fast Video Semantic Segmentation](https://mlsanity.com/paper/2004.01800/) (2020)
- [Low-Latency Video Semantic Segmentation](https://mlsanity.com/paper/1804.00389/) (2018)
- [SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/1909.08291/) (2019)
- [Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling](https://mlsanity.com/paper/2011.14497/) (2020)
- [VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes](https://mlsanity.com/paper/1809.00226/) (2018)
- [Local Memory Attention for Fast Video Semantic Segmentation](https://mlsanity.com/paper/2101.01715/) (2021)
- [Multi Projection Fusion for Real-time Semantic Segmentation of 3D LiDAR Point Clouds](https://mlsanity.com/paper/2011.01974/) (2020)
- [Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)](https://mlsanity.com/paper/1803.07289/) (2018)

## Abstract (arXiv)

Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment. However despite the sensor outputs from autonomous vehicles being naturally temporal in nature, there is still limited exploration of exploiting point cloud sequences for 3D seman-tic segmentation. In this paper we propose a novel Sparse Temporal Local Attention (STELA) module which aggregates intermediate features from a local neighbourhood in previous point cloud frames to provide a rich temporal context to the decoder. Using the sparse local neighbourhood enables our approach to gather features more flexibly than those which directly match point features, and more efficiently than those which perform expensive global attention over the whole point cloud frame. We achieve a competitive mIoU of 64.3% on the SemanticKitti dataset, and demonstrate significant improvement over the single-frame baseline in our ablation studies.