WS-3D-Lane: Weakly Supervised 3D Lane Detection With 2D Lane Labels
Jianyong Ai,Wenbo Ding,Jiuhua Zhao,Jiachen Zhong,Jianyong Ai,Wenbo Ding,Jiuhua Zhao,Jiachen Zhong
Compared to 2D lanes, real 3D lane data is difficult to collect accurately. In this paper, we propose a novel method for training 3D lanes with only 2D lane labels, called weakly supervised 3D lane detection WS-3D-Lane. By assumptions of constant lane width and equal height on adjacent lanes, we indirectly supervise 3D lane heights in the training. To overcome the problem of the dynamic change of ...
