This paper presents a novel CNN-based approach for synthesizing high-resolution LiDAR point cloud data. Our approach generates semantically and perceptually realistic results with guidance from specialized loss-functions. First, we utilize a modified per-point loss that addresses missing LiDAR point measurements. Second, we align the quality of our generated output with real-world sensor data by applying a perceptual loss. In large-scale experiments on real-world datasets, we evaluate both the geometric accuracy and semantic segmentation performance using our generated data vs. ground truth. In a mean opinion score testing we further assess the perceptual quality of our generated point clouds. Our results demonstrate a significant quantitative and qualitative improvement in both geometry and semantics over traditional non CNN-based up-sampling methods.
@article{arxiv.1907.00787,
title = {CNN-based synthesis of realistic high-resolution LiDAR data},
author = {Larissa T. Triess and David Peter and Christoph B. Rist and Markus Enzweiler and J. Marius Zöllner},
journal= {arXiv preprint arXiv:1907.00787},
year = {2021}
}