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.
@article{arxiv.2507.08494,
title = {One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking},
author = {Martin Engilberge and Ivan Vrkic and Friedrich Wilke Grosche and Julien Pilet and Engin Turetken and Pascal Fua},
journal= {arXiv preprint arXiv:2507.08494},
year = {2026}
}