Dense-depth map guided deep Lidar-Visual Odometry with Sparse Point Clouds and Images

TL;DR

This paper introduces a novel LiDAR-Visual odometry framework that combines dense-depth maps, multi-scale feature extraction, and hierarchical pose refinement to improve accuracy and robustness in pose estimation for autonomous systems.

Contribution

It presents a new integration of dense-depth maps with multi-scale attention-based features and hierarchical refinement for enhanced odometry performance.

Findings

Achieves comparable or superior accuracy on KITTI benchmark.

Improves robustness in occlusion and dynamic environments.

Effectively combines LiDAR and image data for pose estimation.

Abstract

Odometry is a critical task for autonomous systems for self-localization and navigation. We propose a novel LiDAR-Visual odometry framework that integrates LiDAR point clouds and images for accurate and robust pose estimation. Our method utilizes a dense-depth map estimated from point clouds and images through depth completion, and incorporates a multi-scale feature extraction network with attention mechanisms, enabling adaptive depth-aware representations. Furthermore, we leverage dense depth information to refine flow estimation and mitigate errors in occlusion-prone regions. Our hierarchical pose refinement module optimizes motion estimation progressively, ensuring robust predictions against dynamic environments and scale ambiguities. Comprehensive experiments on the KITTI odometry benchmark demonstrate that our approach achieves similar or superior accuracy and robustness compared to state-of-the-art visual and LiDAR odometry methods.