TraVeLGAN: Image-to-image Translation by Transformation Vector Learning
Preprint
Abstract
Interest in image-to-image translation has grown substantially in recent years with the success of unsupervised models based on the cycle-consistency assumption. The achievements of these models have been limited to a particular subset of domains where this assumption yields good results, namely homogeneous domains that are characterized by style or texture differences. We tackle the challenging problem of image-to-image translation where the domains are defined by high-level shapes and contexts, as well as including significant clutter and heterogeneity. For this purpose, we introduce a novel GAN based on preserving intra-domain vector transformations in a latent space learned by a siamese network. The traditional GAN system introduced a discriminator network to guide the generator into generating images in the target domain. To this two-network system we add a third: a siamese network that guides the generator so that each original image shares semantics with its generated version. With this new three-network system, we no longer need to constrain the generators with the ubiquitous cycle-consistency restraint. As a result, the generators can learn mappings between more complex domains that differ from each other by large differences - not just style or texture.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings2020
- StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation2018
- ComboGAN: Unrestrained Scalability for Image Domain Translation2018
- From Source to Target and Back: Symmetric Bi-Directional Adaptive GAN2018
- DualGAN: Unsupervised Dual Learning for Image-to-Image Translation2017
- Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization2017
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Style Transfer Via Image Component AnalysisIEEE Transactions on Multimedia, 2013