CoMoGAN: continuous model-guided image-to-image translation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

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

Résumé

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, it outperforms the literature. Our code is available at http://github.com/cv-rits/CoMoGAN .

Dates et versions

hal-03359098 , version 1 (29-09-2021)

Identifiants

Citer

Fabio Pizzati, Pietro Cerri, Raoul de Charette. CoMoGAN: continuous model-guided image-to-image translation. CVPR 2021 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2021, Online, France. ⟨hal-03359098⟩

Collections

INRIA INRIA2
63 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More