Compensated Visual Hull for Defective Segmentation and Occlusion

Abstract

We propose an advanced visual hull technique to compensate for outliers using the reliabilities of the silhouettes. The proposed method consists of a foreground extraction technique based on the generalized Gaussian family model and a compensated shape-from-silhouette algorithm. They are connected by the intra-/inter-silhouette reliabilities to compensate for carving errors from defective segmentation or partial occlusion which may occur in a real environment. The 3D reconstruction process is implemented on a graphics processing unit (GPU) to accelerate the processing speed by using the huge computational power of modern graphics hardware. Experimental results show that the proposed method provides reliable silhouette information and an accurate visual hull in real environments at a very high speed on a common PC.