Chih-Sheng Huang

Stands on Shoulders of Giants: Learning to Lift 2D Detection to 3D with Geometry-Driven Objectives

3D detection of vehicles is an essential component for autonomous driving applications. Nevertheless, collecting the supervised training data for learning 3D vehicle detectors would be costly (e.g. utilization of expensive LiDAR sensors) and labor-intensive (for human annotation). In comparison to 3