Cycle-GAN: Unpaired Image-to-Image Translation

Cycle-GAN: Unpaired Image-to-Image Translation

Tensorflow Implementation of the paper: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

Artificial Intelligence

  • 0 Collaborators

  • 0 Followers

    Follow

Description

Created Tensorflow implementation of the paper: "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks" by Zhu et al. (Mar 2017) arXiv:1703.10593 [cs.CV], along with Graphical visualizations on Tensorboard. Trained the Neural networks for this on Cloud, AWS EC2 GPU Instance.

Given any two unordered image collections, the system learns to automatically “translate” an image from one into the other and vice versa

For example, Transitively converting a Monet painting into a photograph, converting the image of a horse into a zebra or translating a summer photo into a snowy winter one.

Gallery

Medium mohan

Mohan N. created project Cycle-GAN: Unpaired Image-to-Image Translation

Medium 8a6bda56 23e5 45f4 9673 ff782b026a1e

Cycle-GAN: Unpaired Image-to-Image Translation

Created Tensorflow implementation of the paper: "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks" by Zhu et al. (Mar 2017) arXiv:1703.10593 [cs.CV], along with Graphical visualizations on Tensorboard. Trained the Neural networks for this on Cloud, AWS EC2 GPU Instance.

Given any two unordered image collections, the system learns to automatically “translate” an image from one into the other and vice versa

For example, Transitively converting a Monet painting into a photograph, converting the image of a horse into a zebra or translating a summer photo into a snowy winter one.

No users to show at the moment.

No users to show at the moment.