An Efficient Multi-Domain Framework for Image-to-Image Translation

11/28/2019
by   Ye Lin, et al.
4

Existing approaches have been proposed to tackle unsupervised image-to-image translation in recent years. However, they mainly focus on one-to-one mappings, making it difficult to handle more general and practical problems such as multi-domain translations. To address issues like large cost of training time and resources in translation between any number of domains, we propose a general framework called multi-domain translator (MDT), which is extended from bi-directional image-to-image translation. MDT is designed to have only one domain-shared encoder for the consideration of efficiency, together with several domain-specified decoders to transform an image into multiple domains without knowing the input domain label. Moreover, we propose to employ two constraints, namely reconstruction loss and identity loss to further improve the generation. Experiments are conducted on different databases for several multi-domain translation tasks. Both qualitative and quantitative results demonstrate the effectiveness and efficiency performed by the proposed MDT against the state-of-the-art models.

READ FULL TEXT

page 8

page 9

page 10

page 11

page 12

page 13

page 15

research
10/11/2018

SingleGAN: Image-to-Image Translation by a Single-Generator Network using Multiple Generative Adversarial Learning

Image translation is a burgeoning field in computer vision where the goa...
research
05/29/2019

Image-to-Image Translation with Multi-Path Consistency Regularization

Image translation across different domains has attracted much attention ...
research
02/26/2019

Harmonic Unpaired Image-to-image Translation

The recent direction of unpaired image-to-image translation is on one ha...
research
03/27/2020

Augmenting Colonoscopy using Extended and Directional CycleGAN for Lossy Image Translation

Colorectal cancer screening modalities, such as optical colonoscopy (OC)...
research
12/06/2017

Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders

Unsupervised Image-to-Image Translation achieves spectacularly advanced ...
research
01/05/2020

Informative Sample Mining Network for Multi-Domain Image-to-Image Translation

The performance of multi-domain image-to-image translation has been sign...
research
12/25/2019

Asymmetric GAN for Unpaired Image-to-image Translation

Unpaired image-to-image translation problem aims to model the mapping fr...

Please sign up or login with your details

Forgot password? Click here to reset