Image Synthesis Applications

dc.contributor.authorNtavelis, Evangelos
dc.contributor.authorShahbazi, Mohamad
dc.contributor.authorLuongo, Francesca
dc.contributor.authorKastanis, Iason
dc.contributor.authorTimofte, Radu
dc.contributor.authorDanelljan, Martin
dc.contributor.authorVan Gool, Luc
dc.date.accessioned2022-05-13T09:41:36Z
dc.date.available2022-05-13T09:41:36Z
dc.date.issued2022-05-12
dc.description.abstractPositional encodings have enabled recent works to train a single adversarial network that can generate images of different scales. However, these approaches are either limited to a set of discrete scales or struggle to maintain good perceptual quality at the scales for which the model is not trained explicitly. We propose the design of scale-consistent positional encodings invariant to our generator's layers transformations. This enables the generation of arbitrary-scale images even at scales unseen during training. Moreover, we incorporate novel inter-scale augmentations into our pipeline and partial generation training to facilitate the synthesis of consistent images at arbitrary scales. Lastly, we show competitive results for a continuum of scales on various commonly used datasets for image synthesisen_US
dc.identifier.citationNtavelis et al, Image Synthesis Applications, DataDays 2022, Zurichen_US
dc.identifier.urihttps://hdl.handle.net/20.500.12839/1014
dc.language.isoenen_US
dc.subjectDeep Learning, Machine Learning, Synthetic Data, GAN, Generative Adversarial Networken_US
dc.titleImage Synthesis Applicationsen_US
dc.typeConferenceen_US
dc.type.csemdivisionsBU-Ren_US
dc.type.csemresearchareasData & AIen_US
dc.type.csemresearchareasIndustry 4.0en_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
imageSynthesisApplicaitons.pdf
Size:
1.29 MB
Format:
Adobe Portable Document Format
Description:
Poster
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.82 KB
Format:
Item-specific license agreed upon to submission
Description: