Breaking the cycle -- Colleagues are all you need
This addresses limitations in GAN-based image translation for tasks like object removal and large shape modifications, though it appears incremental as an alternative to cycle-based approaches.
The paper tackles unpaired image-to-image translation by replacing cycle constraints with collaborative GANs, resulting in a multi-modal method that generates diverse images and outperforms state-of-the-art methods in challenging applications.
This paper proposes a novel approach to performing image-to-image translation between unpaired domains. Rather than relying on a cycle constraint, our method takes advantage of collaboration between various GANs. This results in a multi-modal method, in which multiple optional and diverse images are produced for a given image. Our model addresses some of the shortcomings of classical GANs: (1) It is able to remove large objects, such as glasses. (2) Since it does not need to support the cycle constraint, no irrelevant traces of the input are left on the generated image. (3) It manages to translate between domains that require large shape modifications. Our results are shown to outperform those generated by state-of-the-art methods for several challenging applications on commonly-used datasets, both qualitatively and quantitatively.