Benutzer: Gast  Login
Titel:

Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition

Dokumenttyp:
Zeitschriftenaufsatz
Autor(en):
Planche, B.; Zakharov, S.; Wu, Z.; Hutter, A.; Kosch, H.; Ilic, S.
Abstract:
While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. It thus became common to use available synthetic samples along domain adaptation schemes to prepare algorithms for the target domain. Tackling this problem from a different angle, we introduce a pipeline to map unseen target samples into the synthetic domain used to train task-specific methods. Denoising the data...     »
Stichworte:
CAMP,CAMPComputerVision,ComputerVision,DomainAdaptation,3DPoseEstimation
Zeitschriftentitel:
International Conference on Intelligent Robots and Systems (IROS)
Jahr:
2019
 BibTeX