Learning to Drop Points for LiDAR Scan Synthesis

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

2 被引用数 (Scopus)

抄録

3D laser scanning by LiDAR sensors plays an important role for mobile robots to understand their surroundings. Nevertheless, not all systems have high resolution and accuracy due to hardware limitations, weather conditions, and so on. Generative modeling of LiDAR data as scene priors is one of the promising solutions to compensate for unreliable or incomplete observations. In this paper, we propose a novel generative model for learning LiDAR data based on generative adversarial networks. As in the related studies, we process LiDAR data as a compact yet lossless representation, a cylindrical depth map. However, despite the smoothness of real-world objects, many points on the depth map are dropped out through the laser measurement, which causes learning difficulty on generative models. To circumvent this issue, we introduce measurement uncertainty into the generation process, which allows the model to learn a disentangled representation of the underlying shape and the dropout noises from a collection of real LiDAR data. To simulate the lossy measurement, we adopt a differentiable sampling framework to drop points based on the learned uncertainty. We demonstrate the effectiveness of our method on synthesis and reconstruction tasks using two datasets. We further showcase potential applications by restoring LiDAR data with various types of corruption.

本文言語英語
ホスト出版物のタイトルIEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
出版社Institute of Electrical and Electronics Engineers Inc.
ページ222-229
ページ数8
ISBN(電子版)9781665417143
DOI
出版ステータス出版済み - 2021
イベント2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021 - Prague, チェコ共和国
継続期間: 9月 27 202110月 1 2021

出版物シリーズ

名前IEEE International Conference on Intelligent Robots and Systems
ISSN(印刷版)2153-0858
ISSN(電子版)2153-0866

会議

会議2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
国/地域チェコ共和国
CityPrague
Period9/27/2110/1/21

!!!All Science Journal Classification (ASJC) codes

  • 制御およびシステム工学
  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識
  • コンピュータ サイエンスの応用

フィンガープリント

「Learning to Drop Points for LiDAR Scan Synthesis」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル