Entropy-regularized Optimal Transport Generative Models
This work addresses image generation for computer vision, but it appears incremental as it builds on existing optimal transport methods with minor improvements.
The paper tackled the problem of learning implicit distributions for image generation by proposing two generative models based on entropy-regularized optimal transport (EOT) cost, showing improved performance on MNIST.
We investigate the use of entropy-regularized optimal transport (EOT) cost in developing generative models to learn implicit distributions. Two generative models are proposed. One uses EOT cost directly in an one-shot optimization problem and the other uses EOT cost iteratively in an adversarial game. The proposed generative models show improved performance over contemporary models for image generation on MNSIT.