Show simple item record

dc.contributor.authorAlharbi, Yazeed
dc.contributor.authorWonka, Peter
dc.date.accessioned2020-05-19T09:15:21Z
dc.date.available2020-05-19T09:15:21Z
dc.date.issued2020-08-05
dc.identifier.citationAlharbi, Y., & Wonka, P. (2020). Disentangled Image Generation Through Structured Noise Injection. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr42600.2020.00518
dc.identifier.isbn978-1-7281-7169-2
dc.identifier.issn1063-6919
dc.identifier.doi10.1109/CVPR42600.2020.00518
dc.identifier.urihttp://hdl.handle.net/10754/662872
dc.description.abstractWe explore different design choices for injecting noise into generative adversarial networks (GANs) with the goal of disentangling the latent space. Instead of traditional approaches, we propose feeding multiple noise codes through separate fully-connected layers respectively. The aim is restricting the influence of each noise code to specific parts of the generated image. We show that disentanglement in the first layer of the generator network leads to disentanglement in the generated image. Through a grid-based structure, we achieve several aspects of disentanglement without complicating the network architecture and without requiring labels. We achieve spatial disentanglement, scale-space disentanglement, and disentanglement of the foreground object from the background style allowing fine-grained control over the generated images. Examples include changing facial expressions in face images, changing beak length in bird images, and changing car dimensions in car images. This empirically leads to better disentanglement scores than state-of-the-art methods on the FFHQ dataset.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/9157760/
dc.relation.urlhttps://ieeexplore.ieee.org/document/9157760/
dc.relation.urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9157760
dc.rightsArchived with thanks to IEEE
dc.titleDisentangled Image Generation Through Structured Noise Injection
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentVisual Computing Center (VCC)
dc.conference.date13-19 June 2020
dc.conference.name2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
dc.conference.locationSeattle, WA, USA
dc.eprint.versionPost-print
dc.identifier.arxivid2004.12411
kaust.personAlHarbi, Yazeed
kaust.personWonka, Peter
refterms.dateFOA2020-05-19T09:16:01Z
dc.date.published-online2020-08-05
dc.date.published-print2020-06
dc.date.posted2020-04-26


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
2.304Mb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record