Improving Style-Content Disentanglement in Image-to-Image Translation
This addresses a specific bottleneck in image-to-image translation for computer vision applications, but it appears incremental as it builds on existing methods.
The paper tackled the problem of style-content entanglement in unsupervised image-to-image translation, which hurts performance, by proposing a principled approach with an additional loss term as a content-bottleneck, resulting in significantly more disentangled representations and improved visual quality and translation diversity.
Unsupervised image-to-image translation methods have achieved tremendous success in recent years. However, it can be easily observed that their models contain significant entanglement which often hurts the translation performance. In this work, we propose a principled approach for improving style-content disentanglement in image-to-image translation. By considering the information flow into each of the representations, we introduce an additional loss term which serves as a content-bottleneck. We show that the results of our method are significantly more disentangled than those produced by current methods, while further improving the visual quality and translation diversity.