KIT | KIT-Bibliothek | Impressum | Datenschutz

Improving 3D Semantic Segmentation withTwin-Representation Networks

Duerr, Fabian ORCID iD icon

Abstract (englisch):

The growing importance of 3d scene understanding and interpretation is inher-ently connected to the rise of autonomous driving and robotics. Semanticsegmentation of 3d point clouds is a key enabler for this task, providing geo-metric information enhanced with semantics. To use Convolutional NeuralNetworks, a proper representation of the point clouds must be chosen. Variousrepresentations have been proposed, with different advantages and disadvantages.In this work, we present a twin-representation architecture, which is composedof a 3d point-based and a 2d range image branch, to efficiently extract and refinepoint-wise features, supported by strong context information. Additionally, afeature propagation strategy is proposed to connect both branches. The approachis evaluated on the challenging SemanticKITTI dataset [2] and considerablyoutperforms the baseline overall as well as for every individual class. Especiallythe predictions for distant points are significantly improved.

Verlagsausgabe §
DOI: 10.5445/IR/1000135074
Veröffentlicht am 06.07.2021
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2021
Sprache Englisch
Identifikator ISBN: 978-3-7315-1091-8
KITopen-ID: 1000135074
Erschienen in Proceedings of the 2020 Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory. Ed.: J. Beyerer; T. Zander
Verlag KIT Scientific Publishing
Seiten 53-65
Serie Karlsruher Schriften zur Anthropomatik / Lehrstuhl für Interaktive Echtzeitsysteme, Karlsruher Institut für Technologie ; Fraunhofer-Inst. für Optronik, Systemtechnik und Bildauswertung IOSB Karlsruhe ; 51
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page