Linking vision and motion for self-supervised object-centric perception

Understand

Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features.

• Traditionally these representations have been obtained via supervised learning, but this decouples perception from the downstream driving task and could harm generalization.
• In this work we adapt a self-supervised object-centric vision model to perform object decomposition using only RGB video and the pose of the vehicle as inputs.
• We demonstrate that our method obtains promising results on the Waymo Open perception dataset.