Unpaired Image-to-Image Translation via Neural Schrödinger Bridge
This addresses a limitation in diffusion models for unpaired translation tasks, offering a novel method for researchers and practitioners in computer vision and generative modeling.
The paper tackles the problem of unpaired image-to-image translation for high-resolution images by proposing Unpaired Neural Schrödinger Bridge (UNSB), which expresses the Schrödinger Bridge problem as adversarial learning problems, and shows it successfully solves various tasks with scalability.
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. Schrödinger 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 Schrödinger 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}