FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

🤖 Plain-English Summary

Monocular 3D object detection is an important task for autonomous driving considering its advantage of low cost. Our solution achieves 1st place out of all the vision-only methods in the nuScenes 3D detection challenge of NeurIPS 2020.

🔑 Key Findings

• It is much more challenging than conventional 2D cases due to its inherent ill-posed property, which is mainly reflected in the lack of depth information.
• Recent progress on 2D detection offers opportunities to better solving this problem.
• However, it is non-trivial to make a general adapted 2D detector work in this 3D task.

🔗 Related Resources