High Detail Marker based 3D Reconstruction by Enforcing Multiview Constraints

We present a 3D reconstruction method enabling high resolution marker-based capturing of deforming surfaces. In contrast to previous work, we allow all markers to look exactly the same and do not rely on temporal tracking. This implies considerable advantages: markers can be smaller and are easier to apply due to omitted identification; long-range motions normally confusing temporal tracking algorithms become feasible. However, the correct matching of markers between camera views is highly ambiguous in such a scenario. To solve this problem we propose an optimization framework that considers multiview conflicts and local smoothness of the captured surface. An iterative relaxation method based on graph matching is adopted to obtain a consistent, smooth reconstruction for all stereo pairs of a multi-camera system simultanously. Preliminary experiments show excellent and robust results.