VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction
Innmann M, Zollhöfer M, Nießner M, Theobald C, Stamminger M (2016)
Publication Language: English
Publication Status: Published
Publication Type: Conference contribution, Conference Contribution
Publication year: 2016
Journal
Publisher: Springer Verlag
City/Town: Cham
Pages Range: 362-379
Conference Proceedings Title: ECCV 2016 - Proceedings of the European Conference on Computer Vision
Event location: Amsterdam
ISBN: 9783319464831
URI: https://www.lgdv.tf.fau.de/?p=425
DOI: 10.1007/978-3-319-46484-8_22
Abstract
We present a novel approach for the reconstruction of dynamic geometric shapes using a single hand-held consumer-grade RGB-D sensor at real-time rates. Our method builds up the scene model from scratch during the scanning process, thus it does not require a predefined shape template to start with. Geometry and motion are parameterized in a unified manner by a volumetric representation that encodes a distance field of the surface geometry as well as the non-rigid space deformation. Motion tracking is based on a set of extracted sparse color features in combination with a dense depth constraint. This enables accurate tracking and drastically reduces drift inherent to standard modelto- depth alignment. We cast finding the optimal deformation of space as a non-linear regularized variational optimization problem by enforcing local smoothness and proximity to the input constraints. The problem is tackled in real-time at the camera’s capture rate using a data-parallel flip-flop optimization strategy. Our results demonstrate robust tracking even for fast motion and scenes that lack geometric features.
Authors with CRIS profile
Related research project(s)
Involved external institutions
United States (USA) (US)How to cite
APA:
Innmann, M., Zollhöfer, M., Nießner, M., Theobald, C., & Stamminger, M. (2016). VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction. In Springer International Publishing (Eds.), ECCV 2016 - Proceedings of the European Conference on Computer Vision (pp. 362-379). Amsterdam, NL: Cham: Springer Verlag.
MLA:
Innmann, Matthias, et al. "VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction." Proceedings of the 14th European Conference on Computer Vision (ECCV), Amsterdam Ed. Springer International Publishing, Cham: Springer Verlag, 2016. 362-379.
BibTeX: Download