3D Surface Reconstruction from Voxel-based Lidar Data
This addresses the need for accurate environmental modeling in autonomous vehicles, but appears incremental as it builds on existing TSDF voxel-based methods.
The paper tackles the problem of 3D surface reconstruction from voxel-based LiDAR data for autonomous vehicle navigation, achieving good performance compared to a state-of-the-art method in evaluations on synthetic and real datasets.
To achieve fully autonomous navigation, vehicles need to compute an accurate model of their direct surrounding. In this paper, a 3D surface reconstruction algorithm from heterogeneous density 3D data is presented. The proposed method is based on a TSDF voxel-based representation, where an adaptive neighborhood kernel sourced on a Gaussian confidence evaluation is introduced. This enables to keep a good trade-off between the density of the reconstructed mesh and its accuracy. Experimental evaluations carried on both synthetic (CARLA) and real (KITTI) 3D data show a good performance compared to a state of the art method used for surface reconstruction.