LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Images
This work addresses scene flow estimation for robotics or autonomous systems, but it appears incremental as it builds on existing fusion techniques.
The authors tackled the problem of dense scene flow estimation by fusing sparse LiDAR with stereo images to address issues like textureless objects and unstructured 3D point matching, resulting in superior performance compared to image-only methods.
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.