Scene Completenesss-Aware Lidar Depth Completion for Driving Scenario
In this paper we propose Scene Completeness-Aware Depth Completion (SADC) to complete raw lidar scans into dense depth maps with fine whole scene structures. Recent sparse depth completion for lidar only focuses on the lower scenes and produce irregular estimations on the upper because existing datasets such as KITTI do not provide groundtruth for upper areas. These areas are considered less important because they are usually sky or trees and of less scene understanding interest. However, we argue that in several driving scenarios such as large trucks or cars with loads, objects could extend to upper parts of scenes, and thus depth maps with structured upper scene estimation are important for RGBD algorithms. SADC leverages stereo cameras, which have better scene completeness, and lidars, which are more precise, to perform sparse depth completion. To our knowledge, we are the first to focus on scene completeness of sparse depth completion. We validate our SADC on both depth estimate precision and scene-completeness on KITTI. Moreover, SADC only adds small extra computational cost upon base methods of stereo matching and lidar completion in terms of runtime and model size.
READ FULL TEXT