Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Back to the future: Learning shape models from 3D CAD data

: Stark, Michael; Goesele, Michael; Schiele, Bernt


Labrosse, F.; Reyer Zwiggelaar; Yonghuai Liu; Bernie Tiddeman ; British Machine Vision Association -BMVA-:
British Machine Vision Conference, BMVC 2010. Proceedings : Aberystwyth, 31st August - 3rd September 2010, Conference Programme & Abstracts
Edinburgh: BMVA, 2010
ISBN: 1-901725-40-5
British Machine Vision Conference (BMVC) <21, 2010, Aberystwyth>
Fraunhofer IGD ()
3D CAD; object recognition; Probabilistic models; non photorealistic rendering; multiple view representation; Forschungsgruppe Capturing Reality (CARE)

Recognizing 3D objects from arbitrary view points is one of the most fundamental problems in computer vision. A major challenge lies in the transition between the 3D geometry of objects and 2D representations that can be robustly matched to natural images. Most approaches thus rely on 2D natural images either as the sole source of training data for building an implicit 3D representation, or by enriching 3D models with natural image features. In this paper, we go back to the ideas from the early days of computer vision, by using 3D object models as the only source of information for building a multi-view object class detector. In particular, we use these models for learning 2D shape that can be robustly matched to 2D natural images. Our experiments confirm the validity of our approach, which outperforms current state-of-the-art techniques on a multi-view detection data set.