N-QGN: Navigation Map from a Monocular Camera using Quadtree Generating Networks
This work addresses the need for efficient depth estimation in autonomous navigation by reducing superfluous details, though it is incremental as it builds on existing self-supervised methods.
The paper tackles the problem of monocular depth estimation for autonomous navigation by proposing a method to estimate navigation maps using a quadtree representation, focusing on essential details for obstacle avoidance while approximating other areas; experiments on the KITTI dataset show it significantly reduces output information without major accuracy loss.
Monocular depth estimation has been a popular area of research for several years, especially since self-supervised networks have shown increasingly good results in bridging the gap with supervised and stereo methods. However, these approaches focus their interest on dense 3D reconstruction and sometimes on tiny details that are superfluous for autonomous navigation. In this paper, we propose to address this issue by estimating the navigation map under a quadtree representation. The objective is to create an adaptive depth map prediction that only extract details that are essential for the obstacle avoidance. Other 3D space which leaves large room for navigation will be provided with approximate distance. Experiment on KITTI dataset shows that our method can significantly reduce the number of output information without major loss of accuracy.