Diversifying Semantic Image Synthesis and Editing via Class- and Layer-wise VAEs

dc.contributor.authorEndo, Yukien_US
dc.contributor.authorKanamori, Yoshihiroen_US
dc.contributor.editorEisemann, Elmar and Jacobson, Alec and Zhang, Fang-Lueen_US
dc.date.accessioned2020-10-29T18:51:14Z
dc.date.available2020-10-29T18:51:14Z
dc.date.issued2020
dc.description.abstractSemantic image synthesis is a process for generating photorealistic images from a single semantic mask. To enrich the diversity of multimodal image synthesis, previous methods have controlled the global appearance of an output image by learning a single latent space. However, a single latent code is often insufficient for capturing various object styles because object appearance depends on multiple factors. To handle individual factors that determine object styles, we propose a class- and layer-wise extension to the variational autoencoder (VAE) framework that allows flexible control over each object class at the local to global levels by learning multiple latent spaces. Furthermore, we demonstrate that our method generates images that are both plausible and more diverse compared to state-of-the-art methods via extensive experiments with real and synthetic datasets in three different domains. We also show that our method enables a wide range of applications in image synthesis and editing tasks.en_US
dc.description.number7
dc.description.sectionheadersImage Manipulation
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14164
dc.identifier.issn1467-8659
dc.identifier.pages519-530
dc.identifier.urihttps://doi.org/10.1111/cgf.14164
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14164
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectArtificial intelligence
dc.subjectImage manipulation
dc.titleDiversifying Semantic Image Synthesis and Editing via Class- and Layer-wise VAEsen_US
Files
Collections