Scene Completeness-Aware Lidar Depth Completion for Driving Scenario
This work addresses the need for complete depth maps in driving scenarios, particularly for objects extending to upper scene areas, though it is incremental as it builds on existing sparse depth completion methods.
The paper tackles the problem of incomplete depth maps in lidar scans by introducing SCADC, which uses stereo images to improve scene completeness, achieving better depth precision and enabling more effective RGBD semantic segmentation in driving scenarios.
This paper introduces Scene Completeness-Aware Depth Completion (SCADC) to complete raw lidar scans into dense depth maps with fine and complete scene structures. Recent sparse depth completion for lidars only focuses on the lower scenes and produces irregular estimations on the upper because existing datasets, such as KITTI, do not provide groundtruth for upper areas. These areas are considered less important since they are usually sky or trees 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 the upper parts of scenes. Thus depth maps with structured upper scene estimation are important for RGBD algorithms. SCADC adopts stereo images that produce disparities with better scene completeness but are generally less precise than lidars, to help sparse lidar depth completion. To our knowledge, we are the first to focus on scene completeness of sparse depth completion. We validate our SCADC on both depth estimate precision and scene-completeness on KITTI. Moreover, we experiment on less-explored outdoor RGBD semantic segmentation with scene completeness-aware D-input to validate our method.