Joint representation of primitive and non-primitive objects for 3D vision

Christiane Sommer, Daniel Cremers

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

4 Zitate (Scopus)

Abstract

The use of structural information in 3D scanning is becoming more and more popular. However, most approaches exploit this structural information either in the form of geometric primitives (mostly planes) or known rigid bodies, but not both. We overcome this limitation and propose an object representation that combines primitive and non-primitive objects using one unified formulation that is based on signed distance fields. Object pose manifolds are introduced to represent the rigid movement of primitives and non-primitives in a natural way. We show that different components of volumetric scanning, such as global trajectory optimization or geometry completion and denoising, benefit from our formulation.

OriginalspracheEnglisch
TitelProceedings - 2018 International Conference on 3D Vision, 3DV 2018
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten160-169
Seitenumfang10
ISBN (elektronisch)9781538684252
DOIs
PublikationsstatusVeröffentlicht - 12 Okt. 2018
Veranstaltung6th International Conference on 3D Vision, 3DV 2018 - Verona, Italien
Dauer: 5 Sept. 20188 Sept. 2018

Publikationsreihe

NameProceedings - 2018 International Conference on 3D Vision, 3DV 2018

Konferenz

Konferenz6th International Conference on 3D Vision, 3DV 2018
Land/GebietItalien
OrtVerona
Zeitraum5/09/188/09/18

Fingerprint

Untersuchen Sie die Forschungsthemen von „Joint representation of primitive and non-primitive objects for 3D vision“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren