Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking
This work introduces PLANET, an end-to-end multi-object tracker designed to move beyond the image plane, and lifts existing 2D tracking datasets into 3D by embedding reconstructed 3D scene geometry into the features and positional encodings used during query formation.
Orcun Cetintas, Guillem Brasó, Tim Meinhardt et al.
· 0 citations