Full name | VolumeDeform: Real-time Volumetric Non-rigid Reconstruction |
Description | 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 pre-defined 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. |
Publication title | VolumeDeform: Real-time Volumetric Non-rigid Reconstruction |
Publication authors | Matthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, Marc Stamminger |
Publication venue | ECCV 2016 |
Publication URL | https://graphics.stanford.edu/~niessner/papers/2016/5volumeDeform/innmann2016deform.pdf |
Input Data Types | Uses Color Input, Uses Depth Input |
Programming language(s) | C++ with CUDA |
Hardware | GeForce 1080Ti |
Website | https://www.lgdv.tf.fau.de/publicationen/volumedeform-real-time-volumetric-non-rigid-reconstruction/ |
Submission creation date | 19 Mar, 2020 |
Last edited | 19 Mar, 2020 |