Unsupervised confidence for LiDAR depth maps and applications
This addresses a critical issue for robotics and autonomous driving by improving depth perception reliability, though it appears incremental as it builds on existing methods for confidence estimation.
The paper tackles the problem of noise and outliers in LiDAR depth maps by proposing an unsupervised framework to estimate confidence, enabling outlier filtering, with experimental results on the KITTI dataset showing it excels at this task.
Depth perception is pivotal in many fields, such as robotics and autonomous driving, to name a few. Consequently, depth sensors such as LiDARs rapidly spread in many applications. The 3D point clouds generated by these sensors must often be coupled with an RGB camera to understand the framed scene semantically. Usually, the former is projected over the camera image plane, leading to a sparse depth map. Unfortunately, this process, coupled with the intrinsic issues affecting all the depth sensors, yields noise and gross outliers in the final output. Purposely, in this paper, we propose an effective unsupervised framework aimed at explicitly addressing this issue by learning to estimate the confidence of the LiDAR sparse depth map and thus allowing for filtering out the outliers. Experimental results on the KITTI dataset highlight that our framework excels for this purpose. Moreover, we demonstrate how this achievement can improve a wide range of tasks.