Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/135860
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | ODAM: Object Detection, Association, and Mapping using Posed RGB Video |
Author: | Li, K. DeTone, D. Chen, S. Vo, M. Reid, I. Rezatofighi, H. Sweeney, C. Straub, J. Newcombe, R. |
Citation: | Proceedings / IEEE International Conference on Computer Vision. IEEE International Conference on Computer Vision, 2021, pp.5978-5988 |
Publisher: | IEEE |
Publisher Place: | online |
Issue Date: | 2021 |
ISBN: | 9781665428125 |
ISSN: | 1550-5499 |
Conference Name: | IEEE/CVF International Conference on Computer Vision (ICCV) (10 Oct 2021 - 17 Oct 2021 : Virtual online) |
Statement of Responsibility: | Kejie Li, Daniel DeTone, Steven Chen, Minh Vo, Ian Reid, Hamid Rezatofighi, Chris Sweeney, Julian Straub, and Richard Newcombe |
Abstract: | Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics. We present ODAM, a system for 3D Object Detection, Association, and Mapping using posed RGB videos. The proposed system relies on a deep learning frontend to detect 3D objects from a given RGB frame and associate them to a global object-based map using a graph neu-al network (GNN). Based on these frame-to-model associations, our back-end optimizes object bounding volumes, represented as super-quadrics, under multi-view geometry constraints and the object scale prior. We validate the proposed system on ScanNet where we show a significant improvement over existing RGB-only methods. |
Rights: | ©2021 IEEE |
DOI: | 10.1109/ICCV48922.2021.00594 |
Grant ID: | http://purl.org/au-research/grants/arc/CE140100016 |
Published version: | https://ieeexplore.ieee.org/xpl/conhome/9709627/proceeding |
Appears in Collections: | Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.