Neural Information Processing Systems http://nips.cc/

However, its performance is still limited as it lacks high-quality annotated datasets for training.

Tothisendweproposeaflow-based image-to-image model, called FlowU-Net with Squeeze modules (FUNS), that allows us to disentangle the features while retaining the ability to generate highquality diverse images from condition images.

The shared part contains information for both domains. The exclusive parts, on the other hand, contain only factors of variation that are particular to each domain.

Conditional score-based diffusion model (SBDM) is for conditional generation of target data with paired data as condition, and has achieved great success in image translation. However, it requires the paired data as condition, and there would be insufficient paired data provided in real-world applications.

Neural Information Processing Systems http://nips.cc/

Implementation of our proposed method and the datasets are now available1.

Modern photo editing tools allow creating realistic manipulated images easily.