This is the authors' abstract. We don't add key points for this paper.
Optimal transport (OT) theory and models have been widely applied in the fields of computer vision, machine learning, and image analysis. Among three typical OT model formulations—the Monge, Kantorovich, and dynamical ones—the Kantorovich formulation with entropic regularization is most commonly used in practice due to its simple computational scheme. The other two formulations are rarely regularized since adding regularization terms brings additional difficulties to their theoretical analysis and numerical algorithms. In this paper, we propose a regularized OT model based on the dynamic formulation. We incorporate a [Formula: see text] regularization term on the momentum field to promote smoothness, and a total variation regularization term on the density field to enhance robustness to noise. We establish the existence and uniqueness of solutions to the regularized dynamic OT model and provide a theoretical analysis based on [Formula: see text]-convergence. Moreover, we develop a primal-dual algorithm to efficiently solve the resulting optimization problem. Numerical experiments on spatial-temporal image generation tasks demonstrate the effectiveness of the proposed model and the stability and efficiency of the proposed numerical algorithm. The proposed regularized dynamical OT model provides a flexible and theoretically grounded framework for image generation tasks in imaging science.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Li et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: