LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Images

TL;DR

LiDAR-Flow introduces a novel method that fuses sparse LiDAR data with stereo images to achieve dense scene flow estimation, overcoming limitations of traditional image-only approaches by leveraging LiDAR accuracy and structured fusion steps.

Contribution

The paper presents a new fusion-based approach for dense scene flow estimation that integrates LiDAR and stereo images, improving robustness and accuracy over existing methods.

Findings

LiDAR-Flow outperforms image-only scene flow methods in accuracy.

The approach effectively handles textureless regions and unstructured 3D points.

Fusion of LiDAR and stereo images enhances robustness in challenging environments.

Abstract

We propose a new approach called LiDAR-Flow to robustly estimate a dense scene flow by fusing a sparse LiDAR with stereo images. We take the advantage of the high accuracy of LiDAR to resolve the lack of information in some regions of stereo images due to textureless objects, shadows, ill-conditioned light environment and many more. Additionally, this fusion can overcome the difficulty of matching unstructured 3D points between LiDAR-only scans. Our LiDAR-Flow approach consists of three main steps; each of them exploits LiDAR measurements. First, we build strong seeds from LiDAR to enhance the robustness of matches between stereo images. The imagery part seeks the motion matches and increases the density of scene flow estimation. Then, a consistency check employs LiDAR seeds to remove the possible mismatches. Finally, LiDAR measurements constraint the edge-preserving interpolation method to fill the remaining gaps. In our evaluation we investigate the individual processing steps of our LiDAR-Flow approach and demonstrate the superior performance compared to image-only approach.