Semantics-Aware Multi-Modal Domain Translation: From LiDAR Point Clouds to Panoramic Color Images

Tiago Cortinhal, Fatih Kurnaz, Eren Erdal Aksoy

ICCVW 2021 pp. 3032-3041

doi:10.1109/ICCVW54120.2021.00338 /iccvw/2021/cortinhal2021iccvw-semanticsaware/

Abstract

In this work, we present a simple yet effective framework to address the domain translation problem between different sensor modalities with unique data formats. By relying only on the semantics of the scene, our modular generative framework can, for the first time, synthesize a panoramic color image from a given full 3D LiDAR point cloud.The framework starts with semantic segmentation of the point cloud, which is initially projected onto a spherical surface. The same semantic segmentation is applied to the corresponding camera image. Next, our new conditional generative model adversarially learns to translate the predicted LiDAR segment maps to the camera image counter-parts. Finally, generated image segments are processed to render the panoramic scene images. We provide a thorough quantitative evaluation on the Semantic-KITTI dataset [4] and show that our proposed framework outperforms other strong baseline models. Our source code is available.

PDF ICCVW Semantic Scholar

Cite

Text

Cortinhal et al. "Semantics-Aware Multi-Modal Domain Translation: From LiDAR Point Clouds to Panoramic Color Images." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00338

Markdown

[Cortinhal et al. "Semantics-Aware Multi-Modal Domain Translation: From LiDAR Point Clouds to Panoramic Color Images." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/cortinhal2021iccvw-semanticsaware/) doi:10.1109/ICCVW54120.2021.00338

BibTeX

@inproceedings{cortinhal2021iccvw-semanticsaware,
  title     = {{Semantics-Aware Multi-Modal Domain Translation: From LiDAR Point Clouds to Panoramic Color Images}},
  author    = {Cortinhal, Tiago and Kurnaz, Fatih and Aksoy, Eren Erdal},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2021},
  pages     = {3032-3041},
  doi       = {10.1109/ICCVW54120.2021.00338},
  url       = {https://mlanthology.org/iccvw/2021/cortinhal2021iccvw-semanticsaware/}
}