One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908739450175488 |
|---|---|
| author | Engilberge, Martin Vrkic, Ivan Grosche, Friedrich Wilke Pilet, Julien Turetken, Engin Fua, Pascal |
| author_facet | Engilberge, Martin Vrkic, Ivan Grosche, Friedrich Wilke Pilet, Julien Turetken, Engin Fua, Pascal |
| contents | This work presents a unified, fully differentiable model for multi-people tracking that learns to associate detections into trajectories without relying on pre-computed tracklets. The model builds a dynamic spatiotemporal graph that aggregates spatial, contextual, and temporal information, enabling seamless information propagation across entire sequences. To improve occlusion handling, the graph can also encode scene-specific information. We also introduce a new large-scale dataset with 25 partially overlapping views, detailed scene reconstructions, and extensive occlusions. Experiments show the model achieves state-of-the-art performance on public benchmarks and the new dataset, with flexibility across diverse conditions. Both the dataset and approach will be publicly released to advance research in multi-people tracking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08494 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking Engilberge, Martin Vrkic, Ivan Grosche, Friedrich Wilke Pilet, Julien Turetken, Engin Fua, Pascal Computer Vision and Pattern Recognition This work presents a unified, fully differentiable model for multi-people tracking that learns to associate detections into trajectories without relying on pre-computed tracklets. The model builds a dynamic spatiotemporal graph that aggregates spatial, contextual, and temporal information, enabling seamless information propagation across entire sequences. To improve occlusion handling, the graph can also encode scene-specific information. We also introduce a new large-scale dataset with 25 partially overlapping views, detailed scene reconstructions, and extensive occlusions. Experiments show the model achieves state-of-the-art performance on public benchmarks and the new dataset, with flexibility across diverse conditions. Both the dataset and approach will be publicly released to advance research in multi-people tracking. |
| title | One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.08494 |