TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images

04/09/2020
by   Jianxin Lin, et al.
7

An unsupervised image-to-image translation (UI2I) task deals with learning a mapping between two domains without paired images. While existing UI2I methods usually require numerous unpaired images from different domains for training, there are many scenarios where training data is quite limited. In this paper, we argue that even if each domain contains a single image, UI2I can still be achieved. To this end, we propose TuiGAN, a generative model that is trained on only two unpaired images and amounts to one-shot unsupervised learning. With TuiGAN, an image is translated in a coarse-to-fine manner where the generated image is gradually refined from global structures to local details. We conduct extensive experiments to verify that our versatile method can outperform strong baselines on a wide variety of UI2I tasks. Moreover, TuiGAN is capable of achieving comparable performance with the state-of-the-art UI2I models trained with sufficient data.

READ FULL TEXT

page 2

page 5

page 10

page 12

page 13

page 17

page 18

page 19

research
09/24/2021

Unaligned Image-to-Image Translation by Learning to Reweight

Unsupervised image-to-image translation aims at learning the mapping fro...
research
04/27/2020

Improving Endoscopic Decision Support Systems by Translating Between Imaging Modalities

Novel imaging technologies raise many questions concerning the adaptatio...
research
04/18/2019

A Novel BiLevel Paradigm for Image-to-Image Translation

Image-to-image (I2I) translation is a pixel-level mapping that requires ...
research
09/18/2019

Extremely Weak Supervised Image-to-Image Translation for Semantic Segmentation

Recent advances in generative models and adversarial training have led t...
research
06/07/2023

GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation

Recent advances in deep learning have witnessed many successful unsuperv...
research
06/17/2021

Federated CycleGAN for Privacy-Preserving Image-to-Image Translation

Unsupervised image-to-image translation methods such as CycleGAN learn t...
research
12/05/2018

Integrated unpaired appearance-preserving shape translation across domains

We address the problem of un-supervised geometric image-to-image transla...

Please sign up or login with your details

Forgot password? Click here to reset