Ajou University repository

GAN Inversion with Semantic Segmentation Map for Image Editing
Citations

SCOPUS

0

Citation Export

Publication Year
2022-01-01
Journal
International Conference on ICT Convergence
Publisher
IEEE Computer Society
Citation
International Conference on ICT Convergence, Vol.2022-October, pp.927-931
Keyword
GAN inversionimage editingimage manipulation
Mesh Keyword
Generative adversarial network inversionImage editingImage manipulationInput imageInversion methodsNetwork inversionReal imagesSegmentation mapSemantic segmentationSemantics Information
All Science Classification Codes (ASJC)
Information SystemsComputer Networks and Communications
Abstract
In this paper, we propose a framework to perform Generative Adversarial Network (GAN) inversion using semantic segmentation map to invert input image into the GAN latent space. Generally, it is still difficult to invert semantic information of input image into GAN latent space. In particular, conventional GAN inversion methods usually suffer from inverting accurate semantic information such as shape of glasses and hairstyle. To this end, we propose a framework that uses the semantic segmentation map of the real image to guide the latent space corresponding to feature map with coarse resolution in the Style-GANv2. Experimental results show that our proposed method generates more accurate images and is possible of detailed editing of input images with a variety of semantic information compared with previous GAN inversion methods.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36813
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85143256715&origin=inward
DOI
https://doi.org/10.1109/ictc55196.2022.9952548
Journal URL
http://ieeexplore.ieee.org/xpl/conferences.jsp
Type
Conference
Funding
ACKNOWLEDGEMENT This work has been supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2022-2018-0-01424) supervised by the IITP(Institute for Information communications Technology Promotion).
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Heo,Yong Seok  Image
Heo,Yong Seok 허용석
Department of Electrical and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.