CoMoGAN: continuous model-guided image-to-image translation

Fabio Pizzati, Pietro Cerri, Raoul De Charette

CoMoGAN is a continuous GAN relying on the unsupervised reorganization of the target data on a functional manifold. To that matter, we introduce a new Functional Instance Normalization layer and residual mechanism, which together disentangle image content from position on target manifold. We rely on naive physics-inspired models to guide the training while allowing private model/translations features. CoMoGAN can be used with any GAN backbone and allows new types of image translation, such as cyclic image translation like timelapse generation, or detached linear translation. On all datasets and metrics, it outperforms the literature. Our code is available at http://github.com/cv-rits/CoMoGAN .

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment