Unsupervised Cross-Domain Image Generation

11/07/2016
by   Yaniv Taigman, et al.
0

We study the problem of transferring a sample in one domain to an analog sample in another domain. Given two related domains, S and T, we would like to learn a generative function G that maps an input sample from S to the domain T, such that the output of a given function f, which accepts inputs in either domains, would remain unchanged. Other than the function f, the training data is unsupervised and consist of a set of samples from each domain. The Domain Transfer Network (DTN) we present employs a compound loss function that includes a multiclass GAN loss, an f-constancy component, and a regularizing component that encourages G to map samples from T to themselves. We apply our method to visual domains including digits and face images and demonstrate its ability to generate convincing novel images of previously unseen entities, while preserving their identity.

READ FULL TEXT

page 5

page 7

page 8

page 9

page 12

page 13

page 14

research
08/26/2018

Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs

We present a framework for translating unlabeled images from one domain ...
research
01/14/2020

Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer

We study the problem of learning to map, in an unsupervised way, between...
research
05/18/2018

XOGAN: One-to-Many Unsupervised Image-to-Image Translation

Unsupervised image-to-image translation aims at learning the relationshi...
research
06/06/2022

Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps

Modern image generative models show remarkable sample quality when train...
research
06/10/2021

Domain Transformer: Predicting Samples of Unseen, Future Domains

The data distribution commonly evolves over time leading to problems suc...
research
06/15/2018

One-Shot Unsupervised Cross Domain Translation

Given a single image x from domain A and a set of images from domain B, ...
research
11/27/2020

Tractable loss function and color image generation of multinary restricted Boltzmann machine

The restricted Boltzmann machine (RBM) is a representative generative mo...

Please sign up or login with your details

Forgot password? Click here to reset