Breaking the cycle - Colleagues are all you need

CVPR 2020


Ori Nizan   

Ayellet Tal

GitHub

Code of the experiments described in our paper and pretrained networks are available on Github.

GitHub

Council-GAN: We introduces a collaborative-based approach for performing image-to-image translation between unpaired domains, avoiding cycle constraints.

Abstract 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.

Applications

Breaking the cycle — Colleagues are all you need