Segmentation Guided Image-to-Image Translation with Adversarial Networks

Recently image-to-image translation has received increasing attention, which aims to map images in one domain to another specific one. Existing methods mainly solve this task via a deep generative model, and focus on exploring the relationship between different domains. However, these methods neglec...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-01
Main Authors: Jiang, Songyao, Tao, Zhiqiang, Fu, Yun
Format: Article
Language:English
Subjects:
Controllability
Domains
Image quality
Image segmentation
Mapping
Semantics
State of the art
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently image-to-image translation has received increasing attention, which aims to map images in one domain to another specific one. Existing methods mainly solve this task via a deep generative model, and focus on exploring the relationship between different domains. However, these methods neglect to utilize higher-level and instance-specific information to guide the training process, leading to a great deal of unrealistic generated images of low quality. Existing methods also lack of spatial controllability during translation. To address these challenge, we propose a novel Segmentation Guided Generative Adversarial Networks (SGGAN), which leverages semantic segmentation to further boost the generation performance and provide spatial mapping. In particular, a segmentor network is designed to impose semantic information on the generated images. Experimental results on multi-domain face image translation task empirically demonstrate our ability of the spatial modification and our superiority in image quality over several state-of-the-art methods.
ISSN:2331-8422