# PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences

arXiv: https://arxiv.org/abs/2205.13713 · HTML: https://mlsanity.com/paper/2205.13713/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 61 references that are in the map.
- First posted on arXiv 27 May 2022.

## Builds on (most cited first, 30 of 39)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [Beyond Short Snippets: Deep Networks for Video Classification](https://mlsanity.com/paper/1503.08909/) (2015)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net](https://mlsanity.com/paper/2012.12395/) (2020)
- [Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning](https://mlsanity.com/paper/1805.10002/) (2018)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1902.09130/) (2019)
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/1910.09165/) (2019)
- [View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition](https://mlsanity.com/paper/1804.07453/) (2018)
- [A Universal Representation Transformer Layer for Few-Shot Image Classification](https://mlsanity.com/paper/2006.11702/) (2020)
- [Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks](https://mlsanity.com/paper/1707.05740/) (2017)
- [CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations](https://mlsanity.com/paper/2008.02792/) (2020)
- [SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition](https://mlsanity.com/paper/1907.13025/) (2019)

## Built on by (most cited first, 30 of 68)

- [From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection](https://mlsanity.com/paper/2304.13455/) (2023)
- [Dynamic 3D Scene Analysis by Point Cloud Accumulation](https://mlsanity.com/paper/2207.12394/) (2022)
- [Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions](https://mlsanity.com/paper/2304.11846/) (2023)
- [Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions](https://mlsanity.com/paper/2206.04129/) (2022)
- [Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding](https://mlsanity.com/paper/2208.00281/) (2022)
- [Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning](https://mlsanity.com/paper/2212.05330/) (2022)
- [Domain generalization of 3D semantic segmentation in autonomous driving](https://mlsanity.com/paper/2212.04245/) (2022)
- [Clustering based Point Cloud Representation Learning for 3D Analysis](https://mlsanity.com/paper/2307.14605/) (2023)
- [PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos](https://mlsanity.com/paper/2305.04075/) (2023)
- [Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos](https://mlsanity.com/paper/2308.09245/) (2023)
- [Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception](https://mlsanity.com/paper/2602.23069/) (2026)
- [Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos](https://mlsanity.com/paper/2308.09247/) (2023)
- [LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels](https://mlsanity.com/paper/2403.15173/) (2024)
- [X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer](https://mlsanity.com/paper/2312.07378/) (2023)
- [VG4D: Vision-Language Model Goes 4D Video Recognition](https://mlsanity.com/paper/2404.11605/) (2024)
- [MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models](https://mlsanity.com/paper/2405.14338/) (2024)
- [3DInAction: Understanding Human Actions in 3D Point Clouds](https://mlsanity.com/paper/2303.06346/) (2023)
- [StepNet: Spatial-temporal Part-aware Network for Isolated Sign Language Recognition](https://mlsanity.com/paper/2212.12857/) (2022)
- [Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data](https://mlsanity.com/paper/2304.03980/) (2023)
- [Explore Human Parsing Modality for Action Recognition](https://mlsanity.com/paper/2401.02138/) (2024)
- [STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition](https://mlsanity.com/paper/2303.18177/) (2023)
- [Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation](https://mlsanity.com/paper/2306.05584/) (2023)
- [Dynamic 3D Point Cloud Sequences as 2D Videos](https://mlsanity.com/paper/2403.01129/) (2024)
- [CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding](https://mlsanity.com/paper/2401.09057/) (2024)
- [Hand-Centric Motion Refinement for 3D Hand-Object Interaction via Hierarchical Spatial-Temporal Modeling](https://mlsanity.com/paper/2401.15987/) (2024)
- [Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation](https://mlsanity.com/paper/2406.18011/) (2024)
- [Diffusion Masked Pretraining for Dynamic Point Cloud](https://mlsanity.com/paper/2605.03639/) (2026)
- [Tri-Efficient Transfer Learning for Point Cloud Videos](https://mlsanity.com/paper/2606.24175/) (2026)
- [Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.11145/) (2023)
- [Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning](https://mlsanity.com/paper/2305.12959/) (2023)

## Abstract (arXiv)

Point cloud sequences are irregular and unordered in the spatial dimension while exhibiting regularities and order in the temporal dimension. Therefore, existing grid based convolutions for conventional video processing cannot be directly applied to spatio-temporal modeling of raw point cloud sequences. In this paper, we propose a point spatio-temporal (PST) convolution to achieve informative representations of point cloud sequences. The proposed PST convolution first disentangles space and time in point cloud sequences. Then, a spatial convolution is employed to capture the local structure of points in the 3D space, and a temporal convolution is used to model the dynamics of the spatial regions along the time dimension. Furthermore, we incorporate the proposed PST convolution into a deep network, namely PSTNet, to extract features of point cloud sequences in a hierarchical manner. Extensive experiments on widely-used 3D action recognition and 4D semantic segmentation datasets demonstrate the effectiveness of PSTNet to model point cloud sequences.