Densification of Airborne Lidar Point Cloud with Fused Encoder-Decoder Networks

This paper presents a density enhancement method for airborne LiDAR point cloud with the corresponding image based on a fused Encoder-Decoder network. Different from terrestrial indoor or outdoor scenes, the variance of objects and depth ranges in the large scale airborne data is challenging. To address the problem of objects at different scales, we propose a RGB and depth fused Encoder-Decoder structure inspired by UNet. In addition, we propose a heuristic method for refining the result if instance segmentation labels are available. Both quantitative and qualitative evaluations are performed on a dataset covering 24km
²
area of Osaka in Japan validates the feasibility of the proposed method for densification of point cloud in large scale environment.