One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking

TL;DR

This paper introduces a unified, differentiable dynamic graph model for multi-people tracking that effectively handles occlusions and diverse scenes, outperforming existing methods on multiple benchmarks.

Contribution

It proposes a novel fully differentiable dynamic graph approach for multi-people tracking, eliminating the need for pre-computed tracklets and incorporating scene-specific information.

Findings

Achieves state-of-the-art results on public benchmarks.

Introduces a new large-scale multi-view dataset with complex occlusions.

Demonstrates flexibility across various tracking conditions.

Abstract

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.