# PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?

arXiv: https://arxiv.org/abs/2208.01957 · HTML: https://mlsanity.com/paper/2208.01957/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 67 references that are in the map.
- First posted on arXiv 3 Aug 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (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)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [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)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [MOTS: Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/1902.03604/) (2019)
- [Learning a Neural Solver for Multiple Object Tracking](https://mlsanity.com/paper/1912.07515/) (2019)
- [Video Panoptic Segmentation](https://mlsanity.com/paper/2006.11339/) (2020)
- [Learning to Track with Object Permanence](https://mlsanity.com/paper/2103.14258/) (2021)
- [GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning](https://mlsanity.com/paper/2006.07327/) (2020)
- [EagerMOT: 3D Multi-Object Tracking via Sensor Fusion](https://mlsanity.com/paper/2104.14682/) (2021)
- [Learning by tracking: Siamese CNN for robust target association](https://mlsanity.com/paper/1604.07866/) (2016)
- [How To Train Your Deep Multi-Object Tracker](https://mlsanity.com/paper/1906.06618/) (2019)
- [4D Panoptic LiDAR Segmentation](https://mlsanity.com/paper/2102.12472/) (2021)
- [Probabilistic 3D Multi-Object Tracking for Autonomous Driving](https://mlsanity.com/paper/2001.05673/) (2020)
- [Track to Reconstruct and Reconstruct to Track](https://mlsanity.com/paper/1910.00130/) (2019)
- [Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor](https://mlsanity.com/paper/1504.02340/) (2015)

## Built on by (most cited first, 29 of 29)

- [ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking](https://mlsanity.com/paper/2308.13229/) (2023)
- [3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking](https://mlsanity.com/paper/2308.06635/) (2023)
- [RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud](https://mlsanity.com/paper/2309.09737/) (2023)
- [ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2303.15334/) (2023)
- [TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses](https://mlsanity.com/paper/2306.05888/) (2023)
- [LEGO: Learning and Graph-Optimized Modular Tracker for Online Multi-Object Tracking with Point Clouds](https://mlsanity.com/paper/2308.09908/) (2023)
- [PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search](https://mlsanity.com/paper/2403.15712/) (2024)
- [RobMOT: Robust 3D Multi-Object Tracking by Observational Noise and State Estimation Drift Mitigation on LiDAR PointCloud](https://mlsanity.com/paper/2405.11536/) (2024)
- [You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking](https://mlsanity.com/paper/2304.08709/) (2023)
- [Zero-Shot 4D Lidar Panoptic Segmentation](https://mlsanity.com/paper/2504.00848/) (2025)
- [3D Multiple Object Tracking on Autonomous Driving: A Literature Review](https://mlsanity.com/paper/2309.15411/) (2023)
- [3D Multi-Object Tracking Based on Uncertainty-Guided Data Association](https://mlsanity.com/paper/2303.01786/) (2023)
- [HybridTrack: A Hybrid Approach for Robust Multi-Object Tracking](https://mlsanity.com/paper/2501.01275/) (2025)
- [DecoderTracker: Decoder-Only Method for Multiple-Object Tracking](https://mlsanity.com/paper/2310.17170/) (2023)
- [InScope: A New Real-world 3D Infrastructure-side Collaborative Perception Dataset for Open Traffic Scenarios](https://mlsanity.com/paper/2407.21581/) (2024)
- [CrossTracker: Robust Multi-modal 3D Multi-Object Tracking via Cross Correction](https://mlsanity.com/paper/2411.18850/) (2024)
- [One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking](https://mlsanity.com/paper/2507.08494/) (2025)
- [BOTT: Box Only Transformer Tracker for 3D Object Tracking](https://mlsanity.com/paper/2308.08753/) (2023)
- [DeepKalPose: An Enhanced Deep-Learning Kalman Filter for Temporally Consistent Monocular Vehicle Pose Estimation](https://mlsanity.com/paper/2404.16558/) (2024)
- [STT: Stateful Tracking with Transformers for Autonomous Driving](https://mlsanity.com/paper/2405.00236/) (2024)
- [MonoDETRNext: Next-Generation Accurate and Efficient Monocular 3D Object Detector](https://mlsanity.com/paper/2405.15176/) (2024)
- [Spb3DTracker: A Robust LiDAR-Based Person Tracker for Noisy Environment](https://mlsanity.com/paper/2408.05940/) (2024)
- [OptiPMB: Enhancing 3D Multi-Object Tracking with Optimized Poisson Multi-Bernoulli Filtering](https://mlsanity.com/paper/2503.12968/) (2025)
- [Towards Accurate State Estimation: Motion Dynamics Kalman Filter for 3D Multi-Object Tracking](https://mlsanity.com/paper/2505.07254/) (2025)
- [ATLASFusion: Aggregation Tracking with Location-Aware Sparse Fusion for Robust Spatio-Temporal Multi-View Pedestrian Tracking](https://mlsanity.com/paper/2509.08421/) (2025)
- [Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking](https://mlsanity.com/paper/2606.23604/) (2026)
- [RegTrack: Simplicity Beneath Complexity in Robust Multi-Modal 3D Multi-Object Tracking](https://mlsanity.com/paper/2409.00618/) (2024)
- [S3MOT: Monocular 3D Object Tracking with Selective State Space Model](https://mlsanity.com/paper/2504.18068/) (2025)
- [Beyond Leaderboard Scores: A Deployment-Focused Protocol for Interpretable Tracking Evaluation in Pedestrian-Centric Environments](https://mlsanity.com/paper/2610.01682/) (2026)

## Abstract (arXiv)

Most (3D) multi-object tracking methods rely on appearance-based cues for data association. By contrast, we investigate how far we can get by only encoding geometric relationships between objects in 3D space as cues for data-driven data association. We encode 3D detections as nodes in a graph, where spatial and temporal pairwise relations among objects are encoded via localized polar coordinates on graph edges. This representation makes our geometric relations invariant to global transformations and smooth trajectory changes, especially under non-holonomic motion. This allows our graph neural network to learn to effectively encode temporal and spatial interactions and fully leverage contextual and motion cues to obtain final scene interpretation by posing data association as edge classification. We establish a new state-of-the-art on nuScenes dataset and, more importantly, show that our method, PolarMOT, generalizes remarkably well across different locations (Boston, Singapore, Karlsruhe) and datasets (nuScenes and KITTI).