Unsupervised confidence for LiDAR depth maps and applications

TL;DR

This paper introduces an unsupervised method to estimate confidence in LiDAR depth maps, enabling outlier filtering and improving downstream tasks in autonomous driving scenarios.

Contribution

The paper presents a novel unsupervised framework for confidence estimation in LiDAR depth maps, addressing noise and outliers without requiring labeled data.

Findings

Outperforms existing methods on KITTI dataset

Enhances downstream perception tasks

Effectively filters out noisy depth data

Abstract

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.