Work

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

Year: 2021

Type: preprint

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 .

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2103.06879

Authors: Pizzati, Fabio, Cerri, Pietro, de Charette, Raoul

Institution: Institut national de recherche en sciences et technologies du numérique

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Grand Équipement National De Calcul Intensif

OpenAlex ID: W4311113161

Cites:

Cited by:

Related to: 10