View-Agnostic Point Cloud Generation for Occlusion Reduction in Aerial Lidar

Occlusions are one of the leading causes of data degradation in lidar. The presence of occlusions reduces the overall aesthetic quality of a point cloud, creating a signature that is specific to that viewpoint and sensor modality. Typically, datasets consist of a series of point clouds with one type of sensor and a limited range of viewpoints. Therefore, when training a dataset with a particular signature, it is challenging to infer scenes outside of the original range of the viewpoints from the training dataset. This work develops a generative network that can predict the area in which an occlusion occurs and furnish the missing points. The output is a complete point cloud that is a more general representation and agnostic to the original viewpoint. We can then use the resulting point cloud as an input for a secondary method such as semantic or instance segmentation. We propose a learned sampling technique that uses the features to inform the point sampling instead of relying strictly on spatial information. We also introduce a new network structure that considers multiple point locations and augmentations to generate parallel features. The network is tested against other methods using our aerial occlusion dataset, DALES Viewpoints Version 2, and also against other point cloud completion networks on the Point Cloud Network (PCN) dataset. We show that it reduces occlusions visually and outperforms state-of-the-art point cloud completion networks in both Chamfers and Earth Mover's Distance (EMD) metrics. We also show that using our occlusion reduction method as a pre-processing step improves semantic segmentation results compared to the same scenes processed without using our method.