Building models capable of generating structured output is a key challenge for AI and robotics. While generative models have been explored on many types of data, little work has been done on synthesizing lidar scans, which play a key role in robot mapping and localization. In this work, we show that one can adapt deep generative models for this task by unravelling lidar scans into a 2D point map. Our approach can generate high quality samples, while simultaneously learning a meaningful latent representation of the data. We demonstrate significant improvements against state-of-the-art point cloud generation methods. Furthermore, we propose a novel data representation that augments the 2D signal with absolute positional information. We show that this helps robustness to noisy and imputed input; the learned model can recover the underlying lidar scan from seemingly uninformative data
@article{arxiv.1812.01180,
title = {Deep Generative Modeling of LiDAR Data},
author = {Lucas Caccia and Herke van Hoof and Aaron Courville and Joelle Pineau},
journal= {arXiv preprint arXiv:1812.01180},
year = {2019}
}