Object surface reconstruction from multi-view images with enhancement driven by image forces

Currently available techniques for surface reconstruction from multi-view images require big number of images in order to assure high surface resolution and precise detail reconstruction. Obtaining such big number of images in some cases is impossible on the other hand it may impose high preparation cost. Therefore, to address the drawback a novel method is presented. The aim of this paper is to present a novel approach for surface reconstruction from multi-view images. This method bases on the visual hull approach. It assumes to be able to reconstruct three dimensional manifold without edge from images, the number of necessary images should be as small as possible, and the quality of reconstructed mesh should be good. Applying this method for four images from dino dataset proved to work well.