1 code implementation • 12 Apr 2020 • Feng Xue, Guirong Zhuo, Ziyuan Huang, Wufei Fu, Zhuoyue Wu, Marcelo H. Ang Jr
Our contributions are twofold: a) a novel dense connected prediction (DCP) layer is proposed to provide better object-level depth estimation and b) specifically for autonomous driving scenarios, dense geometrical constrains (DGC) is introduced so that precise scale factor can be recovered without additional cost for autonomous vehicles.
Ranked #54 on Monocular Depth Estimation on KITTI Eigen split