# Spatiotemporal Self-supervised Learning for Point Clouds in the Wild

arXiv: https://arxiv.org/abs/2303.16235 · HTML: https://mlsanity.com/paper/2303.16235/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 48 references that are in the map.
- First posted on arXiv 28 Mar 2023.

## Builds on (most cited first, 30 of 35)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts](https://mlsanity.com/paper/2012.09165/) (2020)
- [Scaling and Benchmarking Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1905.01235/) (2019)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network](https://mlsanity.com/paper/2102.04530/) (2021)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances](https://mlsanity.com/paper/2002.09147/) (2020)
- [Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks](https://mlsanity.com/paper/1701.04722/) (2017)
- [Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap](https://mlsanity.com/paper/2203.13457/) (2022)
- [Self-Supervised Learning for Domain Adaptation on Point-Clouds](https://mlsanity.com/paper/2003.12641/) (2020)
- [Deep Subspace Clustering Networks](https://mlsanity.com/paper/1709.02508/) (2017)
- [ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2207.12654/) (2022)

## Built on by (most cited first, 23 of 23)

- [Three Pillars improving Vision Foundation Model Distillation for Lidar](https://mlsanity.com/paper/2310.17504/) (2023)
- [4D Contrastive Superflows are Dense 3D Representation Learners](https://mlsanity.com/paper/2407.06190/) (2024)
- [BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds](https://mlsanity.com/paper/2310.17281/) (2023)
- [WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments](https://mlsanity.com/paper/2312.15364/) (2023)
- [A Survey of Generative Techniques for Spatial-Temporal Data Mining](https://mlsanity.com/paper/2405.09592/) (2024)
- [Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object Detection](https://mlsanity.com/paper/2501.04969/) (2025)
- [Refining CLIP's Spatial Awareness: A Visual-Centric Perspective](https://mlsanity.com/paper/2504.02328/) (2025)
- [T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learning](https://mlsanity.com/paper/2312.10217/) (2023)
- [Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2308.10016/) (2023)
- [Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception](https://mlsanity.com/paper/2405.07201/) (2024)
- [Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration](https://mlsanity.com/paper/2401.12452/) (2024)
- [Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations](https://mlsanity.com/paper/2507.05260/) (2025)
- [Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange](https://mlsanity.com/paper/2404.07504/) (2024)
- [UNIT: Unsupervised Online Instance Segmentation through Time](https://mlsanity.com/paper/2409.07887/) (2024)
- [Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining](https://mlsanity.com/paper/2503.19912/) (2025)
- [Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving](https://mlsanity.com/paper/2402.15583/) (2024)
- [TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception](https://mlsanity.com/paper/2412.03054/) (2024)
- [TerraSeg: Self-Supervised Ground Segmentation for Any LiDAR](https://mlsanity.com/paper/2603.27344/) (2026)
- [Exploring the Untouched Sweeps for Conflict-Aware 3D Segmentation Pretraining](https://mlsanity.com/paper/2407.07465/) (2024)
- [Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2410.06893/) (2024)
- [Reliable-loc: Robust sequential LiDAR global localization in large-scale street scenes based on verifiable cues](https://mlsanity.com/paper/2411.07815/) (2024)
- [AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving](https://mlsanity.com/paper/2601.01762/) (2026)
- [MILAN: Milli-Annotations for Lidar Semantic Segmentation](https://mlsanity.com/paper/2407.15797/) (2024)

## Abstract (arXiv)

Self-supervised learning (SSL) has the potential to benefit many applications, particularly those where manually annotating data is cumbersome. One such situation is the semantic segmentation of point clouds. In this context, existing methods employ contrastive learning strategies and define positive pairs by performing various augmentation of point clusters in a single frame. As such, these methods do not exploit the temporal nature of LiDAR data. In this paper, we introduce an SSL strategy that leverages positive pairs in both the spatial and temporal domain. To this end, we design (i) a point-to-cluster learning strategy that aggregates spatial information to distinguish objects; and (ii) a cluster-to-cluster learning strategy based on unsupervised object tracking that exploits temporal correspondences. We demonstrate the benefits of our approach via extensive experiments performed by self-supervised training on two large-scale LiDAR datasets and transferring the resulting models to other point cloud segmentation benchmarks. Our results evidence that our method outperforms the state-of-the-art point cloud SSL methods.