<ul><li>Optimal Transport (OT) theory investigates the cost-minimizing transport map that moves a source distribution to a target distribution.</li><li>Existing methods for learning the optimal transport map using neural networks often experience training instability and sensitivity to hyperparameters.</li><li>A novel method called Displacement Interpolation Optimal Transport Model (DIOTM) is proposed to improve stability and achieve a better approximation of the OT Map.</li><li>DIOTM outperforms existing OT-based models on image-to-image translation tasks.</li></ul>

Improving Neural Optimal Transport via Displacement Interpolation

Discover more