Diffusion models are a powerful class of generative models which simulate stochastic differential equations (SDEs) to generate data from noise. While diffusion models have achieved remarkable progress, they have limitations in unpaired image-to-image (I2I) translation tasks due to the Gaussian prior assumption. Schr\"{o}dinger Bridge (SB), which learns an SDE to translate between two arbitrary distributions, have risen as an attractive solution to this problem. Yet, to our best knowledge, none of SB models so far have been successful at unpaired translation between high-resolution images. In this work, we propose Unpaired Neural Schr\"{o}dinger Bridge (UNSB), which expresses the SB problem as a sequence of adversarial learning problems. This allows us to incorporate advanced discriminators and regularization to learn a SB between unpaired data. We show that UNSB is scalable and successfully solves various unpaired I2I translation tasks. Code: \url{https://github.com/cyclomon/UNSB}

翻译：扩散模型是一类强大的生成模型，它通过模拟随机微分方程从噪声中生成数据。尽管扩散模型取得了显著进展，但由于高斯先验假设，其在无配对图像到图像翻译任务中存在局限性。薛定谔桥通过学习一个在两个任意分布之间进行转换的随机微分方程，已成为解决该问题的有吸引力的方案。然而，据我们所知，目前尚无薛定谔桥模型成功实现高分辨率图像的无配对翻译。在这项工作中，我们提出了无配对神经薛定谔桥（UNSB），将薛定谔桥问题表达为一系列对抗性学习问题。这使得我们能够融合先进的判别器和正则化方法，学习无配对数据之间的薛定谔桥。我们证明UNSB具有可扩展性，并成功解决了多种无配对图像到图像翻译任务。代码：\url{https://github.com/cyclomon/UNSB}