Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks

05/17/2021
by   Sho Inoue, et al.
17

Unpaired image-to-image translation using Generative Adversarial Networks (GAN) is successful in converting images among multiple domains. Moreover, recent studies have shown a way to diversify the outputs of the generator. However, since there are no restrictions on how the generator diversifies the results, it is likely to translate some unexpected features. In this paper, we propose Style-Restricted GAN (SRGAN), a novel approach to transfer input images into different domains' with different styles, changing the exclusively class-related features. Additionally, instead of KL divergence loss, we adopt 3 new losses to restrict the distribution of the encoded features: batch KL divergence loss, correlation loss, and histogram imitation loss. The study reports quantitative as well as qualitative results with Precision, Recall, Density, and Coverage. The proposed 3 losses lead to the enhancement of the level of diversity compared to the conventional KL loss. In particular, SRGAN is found to be successful in translating with higher diversity and without changing the class-unrelated features in the CelebA face dataset. Our implementation is available at https://github.com/shinshoji01/Style-Restricted_GAN.

READ FULL TEXT

page 5

page 12

page 13

page 14

page 15

page 16

page 17

page 18

research
12/08/2021

Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN

Adverse weather image translation belongs to the unsupervised image-to-i...
research
09/16/2020

SLGAN: Style- and Latent-guided Generative Adversarial Network for Desirable Makeup Transfer and Removal

There are five features to consider when using generative adversarial ne...
research
07/29/2020

Translate the Facial Regions You Like Using Region-Wise Normalization

Though GAN (Generative Adversarial Networks) based technique has greatly...
research
01/11/2019

CSGAN: Cyclic-Synthesized Generative Adversarial Networks for Image-to-Image Transformation

The primary motivation of Image-to-Image Transformation is to convert an...
research
11/29/2017

Photo-to-Caricature Translation on Faces in the Wild

Recently, image-to-image translation has been made much progress owing t...
research
10/29/2020

Exploring Generative Adversarial Networks for Image-to-Image Translation in STEM Simulation

The use of accurate scanning transmission electron microscopy (STEM) ima...

Please sign up or login with your details

Forgot password? Click here to reset