An Interactive Tuning Method for Generator Networks Trained by GAN

Simple item page
dc.contributor.authorZhou, Mengyuanen_US
dc.contributor.authorYamaguchi, Yasushien_US
dc.contributor.editorCabiddu, Danielaen_US
dc.contributor.editorSchneider, Teseoen_US
dc.contributor.editorAllegra, Darioen_US
dc.contributor.editorCatalano, Chiara Evaen_US
dc.contributor.editorCherchi, Gianmarcoen_US
dc.contributor.editorScateni, Riccardoen_US
dc.date.accessioned2022-11-08T11:44:46Z
dc.date.available2022-11-08T11:44:46Z
dc.date.issued2022
dc.description.abstractThe recent studies on GAN achieved impressive results in image synthesis. However, they are still not so perfect that output images may contain unnatural regions. We propose a tuning method for generator networks trained by GAN to improve their results by interactively removing unexpected objects and textures or changing the object colors. Our method could find and ablate those units in the generator networks that are highly related to the specific regions or their colors. Compared to the related studies, our proposed method can tune pre-trained generator networks without relying on any additional information like segmentation-based networks. We built the interactive system based on our method, capable of tuning the generator networks to make the resulting images as expected. The experiments show that our method could remove only unexpected objects and textures. It could change the selected area color as well. The method also gives us some hints to discuss the properties of generator networks which layers and units are associated with objects, textures, or colors.en_US
dc.description.sectionheadersMachine Learning for Graphics
dc.description.seriesinformationSmart Tools and Applications in Graphics - Eurographics Italian Chapter Conference
dc.identifier.doi10.2312/stag.20221269
dc.identifier.isbn978-3-03868-191-5
dc.identifier.issn2617-4855
dc.identifier.pages151-160
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/stag.20221269
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/stag20221269
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Image processing; Neural networks; Human-centered computing -> Empirical studies in interaction design
dc.subjectComputing methodologies
dc.subjectImage processing
dc.subjectNeural networks
dc.subjectHuman
dc.subjectcentered computing
dc.subjectEmpirical studies in interaction design
dc.titleAn Interactive Tuning Method for Generator Networks Trained by GANen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
151-160.pdf
Size:
5.36 MB
Format:
Adobe Portable Document Format
Download
Collections
Italian Chapter Conference 2022 - Smart Tools and Apps in Graphics