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

2021/03/11 by Pizzati, Fabio, Cerri, Pietro, de Charette, Raoul · 1 citation
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2103.06879

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 .

Cited by

• TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views

Related

• UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation
• Rethinking conditional GAN training: An approach using geometrically structured latent manifolds
• TraVeLGAN: Image-to-image Translation by Transformation Vector Learning
• LocoGAN -- Locally Convolutional GAN
• Vit-GAN: Image-to-image Translation with Vision Transformes and Conditional GANS