3M3D: Multi-view, Multi-path, Multi-representation for 3D Object Detection

Understand

3D visual perception tasks based on multi-camera images are essential for autonomous driving systems.

• Latest work in this field performs 3D object detection by leveraging multi-view images as an input and iteratively enhancing object queries (object proposals) by cross-attending multi-view features.
• However, individual backbone features are not updated with multi-view features and it stays as a mere collection of the output of the single-image backbone network.
• Therefore we propose 3M3D: A Multi-view, Multi-path, Multi-representation for 3D Object Detection where we update both multi-view features and query features to enhance the representation of the scene in both fine panoramic view and coarse global view.