Simulated tearing: an algorithm for discontinuity-preserving visual surface reconstruction

An algorithm is introduced for discontinuity-preserving visual surface reconstruction, inspired by the formulation of the problem as the fitting of a weak membrane to the observed data. The method slowly applies the data `force´ to a weak membrane, which is allowed to tear when the tension exceeds a certain threshold. The algorithm is named simulated tearing (ST). Formally, ST is a deterministic continuation method, i.e., the problem to be solved is embedded in a family of problems, of which the first member has a simple solution. The proposed method is tested and compared with mean field annealing (MFA), using real and synthetic images. It is concluded that ST is simpler, faster, and slightly outperforms MFA. ST allows implementation based on integer arithmetic