Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understanding

November 2020

tl;dr: CenterNet-based approach, with better distance estimation

Overall impression

Authors from TUD, Germany. The paper proposed two approaches for distance estimation. One is based on DORN with better discretization strategy, and the second is based on breaking down the distance into two large bins, one for near objects and the other for faraway ones.

Overall this paper is a very solid contribution to monocular 3D object detection. Nothing fancy, but concrete experiment and small design tweaks.

A quick summary of CenterNet monocular 3D object detection.

Key ideas

Technical details