Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Deep learning for occlusion aware RGB-D image completion for structured light measurements

: Siegmund, F.; Spehr, M.; Höhne, D.; Notni, G.


Tian, L. ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Computational Imaging V : 27 April - 8 May 2020, Online Only, United States
Bellingham, WA: SPIE, 2020 (Proceedings of SPIE 11396)
ISBN: 978-1-5106-3569-2
ISBN: 978-1-5106-3570-8
Paper 113960G, 15 S.
Conference "Computational Imaging" <5, 2020, Online>
Fraunhofer IOF ()

In our work we propose a deep learning solution to complete RGB-D images that are acquired by a NIR structured light scanner with an additional RGB camera that measures the visible spectrum. Building on works on image inpainting, we designed and trained a neural network architecture that takes the available fringe and color images as well as the reliably measured depth information and completes the depth images. We particularly focus on occlusion-caused image artifacts that naturally occur due to geometric visibility constraints. Hence, we are able to reconstruct a dense depth image from the viewpoint of the RGB camera, which can be used for further post-processing and visualization purposes.