UVCGAN v2: An Improved Cycle-Consistent GAN for Unpaired Image-to-Image Translation
This work addresses the problem of unpaired image-to-image translation for computer vision researchers, offering a competitive alternative to diffusion models with significant performance gains, though it is incremental as it builds on an existing GAN-based approach.
The authors tackled unpaired image-to-image translation by improving the UVCGAN model with modern architectures and training procedures, achieving over 40% improvement in FID score on Male-to-Female CelebA translation compared to state-of-the-art results.
An unpaired image-to-image (I2I) translation technique seeks to find a mapping between two domains of data in a fully unsupervised manner. While initial solutions to the I2I problem were provided by generative adversarial neural networks (GANs), diffusion models (DMs) currently hold the state-of-the-art status on the I2I translation benchmarks in terms of Frechet inception distance (FID). Yet, DMs suffer from limitations, such as not using data from the source domain during the training or maintaining consistency of the source and translated images only via simple pixel-wise errors. This work improves a recent UVCGAN model and equips it with modern advancements in model architectures and training procedures. The resulting revised model significantly outperforms other advanced GAN- and DM-based competitors on a variety of benchmarks. In the case of Male-to-Female translation of CelebA, the model achieves more than 40% improvement in FID score compared to the state-of-the-art results. This work also demonstrates the ineffectiveness of the pixel-wise I2I translation faithfulness metrics and suggests their revision. The code and trained models are available at https://github.com/LS4GAN/uvcgan2