Gap Completion in Point Cloud Scene occluded by Vehicles using SGC-Net

TL;DR

This paper introduces SGC-Net, a deep learning model that effectively fills occluded gaps in urban point cloud scenes caused by vehicles, improving scene reconstruction accuracy in mobile mapping applications.

Contribution

We propose a novel scene gap completion method using virtual vehicle placement and ray-casting to generate training data, along with the SGC-Net model for accurate urban scene reconstruction.

Findings

97.66% of filled points within 5 cm of ground truth

Generated diverse urban scenes with and without occlusion

SGC-Net outperforms existing methods in gap filling accuracy

Abstract

Recent advances in mobile mapping systems have greatly enhanced the efficiency and convenience of acquiring urban 3D data. These systems utilize LiDAR sensors mounted on vehicles to capture vast cityscapes. However, a significant challenge arises due to occlusions caused by roadside parked vehicles, leading to the loss of scene information, particularly on the roads, sidewalks, curbs, and the lower sections of buildings. In this study, we present a novel approach that leverages deep neural networks to learn a model capable of filling gaps in urban scenes that are obscured by vehicle occlusion. We have developed an innovative technique where we place virtual vehicle models along road boundaries in the gap-free scene and utilize a ray-casting algorithm to create a new scene with occluded gaps. This allows us to generate diverse and realistic urban point cloud scenes with and without vehicle occlusion, surpassing the limitations of real-world training data collection and annotation. Furthermore, we introduce the Scene Gap Completion Network (SGC-Net), an end-to-end model that can generate well-defined shape boundaries and smooth surfaces within occluded gaps. The experiment results reveal that 97.66% of the filled points fall within a range of 5 centimeters relative to the high-density ground truth point cloud scene. These findings underscore the efficacy of our proposed model in gap completion and reconstructing urban scenes affected by vehicle occlusions.