Scribble-Supervised LiDAR Semantic Segmentation


Loading...

Date

2022

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Densely annotating LiDAR point clouds remains too expensive and time-consuming to keep up with the ever growing volume of data. While current literature focuses on fully-supervised performance, developing efficient methods that take advantage of realistic weak supervision have yet to be explored. In this paper, we propose using scribbles to annotate LiDAR point clouds and release ScribbleKITTI, the first scribble-annotated dataset for LiDAR semantic segmentation. Furthermore, we present a pipeline to reduce the performance gap that arises when using such weak annotations. Our pipeline comprises of three stand-alone contributions that can be combined with any LiDAR semantic segmentation model to achieve up to 95.7% of the fully-supervised performance while using only 8% labeled points. Our scribble annotations and code are available at github.com/ouenal/scribblekitti.

Publication status

published

Editor

Book title

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Journal / series

Volume

Pages / Article No.

2687 - 2697

Publisher

IEEE

Event

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Segmentation; grouping and shape analysis; Navigation and autonomous driving; Self-& semi-& meta- & unsupervised learning

Organisational unit

03514 - Van Gool, Luc (emeritus) / Van Gool, Luc (emeritus) check_circle

Notes

Funding

Related publications and datasets