Composable Unpaired Image to Image Translation

04/16/2018
by   Laura Graesser, et al.
0

There has been remarkable recent work in unpaired image-to-image translation. However, they're restricted to translation on single pairs of distributions, with some exceptions. In this study, we extend one of these works to a scalable multidistribution translation mechanism. Our translation models not only converts from one distribution to another but can be stacked to create composite translation functions. We show that this composite property makes it possible to generate images with characteristics not seen in the training set. We also propose a decoupled training mechanism to train multiple distributions separately, which we show, generates better samples than isolated joint training. Further, we do a qualitative and quantitative analysis to assess the plausibility of the samples. The code is made available at https://github.com/lgraesser/im2im2im.

READ FULL TEXT

page 3

page 6

page 7

page 8

research
03/02/2017

Unsupervised Image-to-Image Translation Networks

Unsupervised image-to-image translation aims at learning a joint distrib...
research
03/07/2023

Generative Modeling with Flow-Guided Density Ratio Learning

We present Flow-Guided Density Ratio Learning (FDRL), a simple and scala...
research
03/11/2021

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

CoMoGAN is a continuous GAN relying on the unsupervised reorganization o...
research
05/24/2023

SAMScore: A Semantic Structural Similarity Metric for Image Translation Evaluation

Image translation has wide applications, such as style transfer and moda...
research
03/10/2023

Adaptive Supervised PatchNCE Loss for Learning H E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs

Immunohistochemical (IHC) staining highlights the molecular information ...
research
03/02/2021

Image-to-image Translation via Hierarchical Style Disentanglement

Recently, image-to-image translation has made significant progress in ac...
research
07/02/2023

Domain Transfer Through Image-to-Image Translation for Uncertainty-Aware Prostate Cancer Classification

Prostate Cancer (PCa) is often diagnosed using High-resolution 3.0 Tesla...

Please sign up or login with your details

Forgot password? Click here to reset