# Graph Neural Networks for 3D Multi-Object Tracking

arXiv: https://arxiv.org/abs/2008.09506 · HTML: https://mlsanity.com/paper/2008.09506/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [PTTR: Relational 3D Point Cloud Object Tracking with Transformer](https://mlsanity.com/paper/2112.02857/) (2021)
- [Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer](https://mlsanity.com/paper/2208.05216/) (2022)
- [Object Tracking in a 360o View: A Novel Perspective on Bridging the Gap to Biomedical Advancements](https://mlsanity.com/paper/2412.01119/) (2024)

## Abstract (arXiv)

3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent work often uses a tracking-by-detection pipeline, where the feature of each object is extracted independently to compute an affinity matrix. Then, the affinity matrix is passed to the Hungarian algorithm for data association. A key process of this pipeline is to learn discriminative features for different objects in order to reduce confusion during data association. To that end, we propose two innovative techniques: (1) instead of obtaining the features for each object independently, we propose a novel feature interaction mechanism by introducing Graph Neural Networks; (2) instead of obtaining the features from either 2D or 3D space as in prior work, we propose a novel joint feature extractor to learn appearance and motion features from 2D and 3D space. Through experiments on the KITTI dataset, our proposed method achieves state-of-the-art 3D MOT performance. Our project website is at http://www.xinshuoweng.com/projects/GNN3DMOT.