Enhancing Lidar Point Cloud Sampling via Colorization and Super-Resolution of Lidar Imagery

TL;DR

This paper introduces a deep learning framework that enhances lidar point cloud sampling by colorizing and super-resolving lidar imagery, leading to more accurate odometry and registration in challenging environments.

Contribution

It presents a novel deep learning-based approach for colorizing and super-resolving lidar images to improve point cloud sampling and odometry estimation, surpassing previous methods.

Findings

Lower translation and rotation errors achieved.

Fewer points needed for accurate registration.

Improved keypoint detection in degraded environments.

Abstract

Recent advancements in lidar technology have led to improved point cloud resolution as well as the generation of 360 degrees, low-resolution images by encoding depth, reflectivity, or near-infrared light within each pixel. These images enable the application of deep learning (DL) approaches, originally developed for RGB images from cameras to lidar-only systems, eliminating other efforts, such as lidar-camera calibration. Compared with conventional RGB images, lidar imagery demonstrates greater robustness in adverse environmental conditions, such as low light and foggy weather. Moreover, the imaging capability addresses the challenges in environments where the geometric information in point clouds may be degraded, such as long corridors, and dense point clouds may be misleading, potentially leading to drift errors. Therefore, this paper proposes a novel framework that leverages DL-based colorization and super-resolution techniques on lidar imagery to extract reliable samples from lidar point clouds for odometry estimation. The enhanced lidar images, enriched with additional information, facilitate improved keypoint detection, which is subsequently employed for more effective point cloud downsampling. The proposed method enhances point cloud registration accuracy and mitigates mismatches arising from insufficient geometric information or misleading extra points. Experimental results indicate that our approach surpasses previous methods, achieving lower translation and rotation errors while using fewer points.