Lidar Upsampling With Sliced Wasserstein Distance

Artem Savkin, Yida Wang, Sebastian Wirkert, Nassir Navab, Federico Tombari

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

Lidar became an important component of the perception systems in autonomous driving. But challenges of training data acquisition and annotation made emphasized the role of the sensor to sensor domain adaptation. In this letter, we address the problem of lidar upsampling. Learning on lidar point clouds is rather a challenging task due to their irregular and sparse structure. Here we propose a method for lidar point cloud upsampling which can reconstruct fine-grained lidar scan patterns. The key idea is to utilize edge-aware dense convolutions for both feature extraction and feature expansion. Additionally applying a more accurate Sliced Wasserstein Distance facilitates learning of the fine lidar sweep structures. This in turn enables our method to employ a one-stage upsampling paradigm without the need for coarse and fine reconstruction. We conduct several experiments to evaluate our method and demonstrate that it provides better upsampling.

Original languageEnglish
Pages (from-to)392-399
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume8
Issue number1
DOIs
StatePublished - 1 Jan 2023

Keywords

  • Autonomous vehicle navigation
  • deep learning for visual perception
  • lidar
  • transfer learning

Fingerprint

Dive into the research topics of 'Lidar Upsampling With Sliced Wasserstein Distance'. Together they form a unique fingerprint.

Cite this