Submitted by Aljaz Bozic.

Submission data

Full nameVolumeDeform: Real-time Volumetric Non-rigid Reconstruction
DescriptionWe 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 titleVolumeDeform: Real-time Volumetric Non-rigid Reconstruction
Publication authorsMatthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, Marc Stamminger
Publication venueECCV 2016
Publication URL
Input Data TypesUses Color Input, Uses Depth Input
Programming language(s)C++ with CUDA
HardwareGeForce 1080Ti
Submission creation date19 Mar, 2020
Last edited19 Mar, 2020

Non-rigid Reconstruction

Method InfoGeometry error (cm)Deformation error (cm)