Video based Outdoor Human Reconstruction
We propose a very convenient system of scanning a human body using only a conventional video camera without the aid of special sensor or controlled illumination. We leverage the SFM calibration results directly and improve the available video based dense 3D reconstruction by integrating the surface smoothness constraints. The point cloud reinforcement is proposed to detect and adjust the conflict point data for the slender and shaky body part. Combined with the silhouette adaptation, the proposed point cloud reinforcement achieves reasonable and plausible mesh reconstruction on these challenging parts. An additional close-shot frames can also be borrowed to refine the pre-reconstructed mesh model, and lead to a colored water tight model. The overall system is approximate to automatic, since only only one or two painting brush interaction is required for robust and high quality multi-view image segmentation. The experiment results on various test sequences demonstrate the effectiveness and the robustness of the proposed method, even under very challenging scenarios when object shaking, varying illumination and texture-less regions happen.