Diffeomorphic Registration Using Sinkhorn Divergences

The diffeomorphic registration framework enables one to define an optimal matching function between two probability measures with respect a data-fidelity loss function. nonconvexity of the optimization problem renders choice this crucial avoid poor local minima. Recent work showed experimentally efficiency entropy-regularized transportation costs, as they are computationally fast and differentiable while having few Following approach, we provide in paper new based on Sinkhorn divergences, unbiased entropic prove statistical consistency rate empirical deformations.