Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Removing the example from example-based photometric stereo

: Ackermann, Jens; Ritz, Martin; Stork, André; Goesele, Michael


Kutulakos, Kiriakos N. (Ed.):
Trends and topics in computer vision. Pt.2 : ECCV 2010 Workshops, Heraklion, Crete, Greece, September 10-11, 2010; revised selected papers
Berlin: Springer, 2012 (Lecture Notes in Computer Science 6554)
ISBN: 978-3-642-35739-8
ISBN: 978-3-642-35740-4
ISBN: 3-642-35739-3
ISSN: 0302-9743
Workshop on Reconstruction and Modeling of Large-Scale 3D Virtual Environments <2010, Heraklion>
European Conference on Computer Vision (ECCV) <11, 2010, Heraklion>
Workshop on Color and Reflectance in Imaging and Computer Vision (CRICV) <2010, Heraklion>
Workshop on Media Retargeting (MRW) <2010, Heraklion>
Workshop on Computer Vision on GPUs (CVGPU) <2010, Heraklion>
Conference Paper
Fraunhofer IGD ()
3D scene reconstruction; photometry; multi-view stereo; computer vision; surface reconstruction; 3D scanning; 3D reconstruction; Forschungsgruppe Capturing Reality (CARE)

We introduce an example-based photometric stereo approach that does not require explicit reference objects. Instead, we use a robust multi-view stereo technique to create a partial reconstruction of the scene which serves as sceneintrinsic reference geometry. Similar to the standard approach, we then transfer normals from reconstructed to unreconstructed regions based on robust photometric matching. In contrast to traditional reference objects, the scene-intrinsic reference geometry is neither noise free nor does it necessarily contain all possible normal directions for given materials. We therefore propose several modifications that allow us to reconstruct high quality normal maps. During integration, we combine both normal and positional information yielding high quality reconstructions. We show results on several datasets including an example based on data solely collected from the Internet.