CNN-based synthesis of realistic high-resolution LiDAR data

Published in IEEE Intelligent Vehicles Symposium (IV), 2019

[pdf] [project] [poster]

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.

Recommended citation:

@inproceedings{triess2019iv,
    title = {CNN-based synthesis of realistic high-resolution LiDAR data},
    author = {Triess, Larissa T. and Peter, David and Rist, Christoph B. and Enzweiler, Markus and Z\"ollner, J. Marius},
    booktitle = {Proc. IEEE Intelligent Vehicles Symposium (IV)},
    year = {2019},
    pages = {1512--1519},
}