English

Generative Range Imaging for Learning Scene Priors of 3D LiDAR Data

Computer Vision and Pattern Recognition 2022-10-24 v1 Robotics Image and Video Processing

Abstract

3D LiDAR sensors are indispensable for the robust vision of autonomous mobile robots. However, deploying LiDAR-based perception algorithms often fails due to a domain gap from the training environment, such as inconsistent angular resolution and missing properties. Existing studies have tackled the issue by learning inter-domain mapping, while the transferability is constrained by the training configuration and the training is susceptible to peculiar lossy noises called ray-drop. To address the issue, this paper proposes a generative model of LiDAR range images applicable to the data-level domain transfer. Motivated by the fact that LiDAR measurement is based on point-by-point range imaging, we train an implicit image representation-based generative adversarial networks along with a differentiable ray-drop effect. We demonstrate the fidelity and diversity of our model in comparison with the point-based and image-based state-of-the-art generative models. We also showcase upsampling and restoration applications. Furthermore, we introduce a Sim2Real application for LiDAR semantic segmentation. We demonstrate that our method is effective as a realistic ray-drop simulator and outperforms state-of-the-art methods.

Keywords

Cite

@article{arxiv.2210.11750,
  title  = {Generative Range Imaging for Learning Scene Priors of 3D LiDAR Data},
  author = {Kazuto Nakashima and Yumi Iwashita and Ryo Kurazume},
  journal= {arXiv preprint arXiv:2210.11750},
  year   = {2022}
}

Comments

Accepted to WACV 2023

R2 v1 2026-06-28T04:09:05.040Z