CoMoGAN: continuous model-guided image-to-image translation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

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

Abstract

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 and versions

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

Identifiers

Cite

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 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More